Merge branch 'linus' into tracing-v28-for-linus-v3

Conflicts:
	init/main.c
	kernel/module.c
	scripts/bootgraph.pl

38 files changed, 1139 insertions, 772 deletions

diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore
new file mode 100644
index 00000000000..c5f676c3c22
--- /dev/null
+++ b/arch/powerpc/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 946daea780f..fdb58253fa5 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -28,13 +28,14 @@ endif
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \
 				   init_task.o process.o systbl.o idle.o \
-				   signal.o
+				   signal.o sysfs.o
 obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o cpu_setup_ppc970.o \
 				   cpu_setup_pa6t.o \
-				   firmware.o sysfs.o nvram_64.o
+				   firmware.o nvram_64.o
+obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
@@ -69,10 +70,10 @@ extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
 obj-y				+= time.o prom.o traps.o setup-common.o \
-				   udbg.o misc.o io.o \
+				   udbg.o misc.o io.o dma.o \
 				   misc_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
-obj-$(CONFIG_PPC64)		+= dma_64.o iommu.o
+obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_PPC_MULTIPLATFORM)	+= prom_init.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 92768d3006f..75c5dd0138f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -122,6 +122,8 @@ int main(void)
 	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
 	DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
 	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
+	DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase));
+	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
 	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
@@ -350,14 +352,15 @@ int main(void)
 #endif
 
 	DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
+	DEFINE(PTE_SIZE, sizeof(pte_t));
 
 #ifdef CONFIG_KVM
 	DEFINE(TLBE_BYTES, sizeof(struct tlbe));
 
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
-	DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb));
 	DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb));
+	DEFINE(VCPU_SHADOW_MOD, offsetof(struct kvm_vcpu, arch.shadow_tlb_mod));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
@@ -369,7 +372,7 @@ int main(void)
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
-	DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid));
+	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index d8f0329b134..26e58630ed7 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -442,28 +442,26 @@ void btext_drawtext(const char *c, unsigned int len)
 
 void btext_drawhex(unsigned long v)
 {
-	char *hex_table = "0123456789abcdef";
-
 	if (!boot_text_mapped)
 		return;
 #ifdef CONFIG_PPC64
-	btext_drawchar(hex_table[(v >> 60) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 56) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 52) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 48) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 44) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 40) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 36) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 32) & 0x0000000FUL]);
+	btext_drawchar(hex_asc_hi(v >> 56));
+	btext_drawchar(hex_asc_lo(v >> 56));
+	btext_drawchar(hex_asc_hi(v >> 48));
+	btext_drawchar(hex_asc_lo(v >> 48));
+	btext_drawchar(hex_asc_hi(v >> 40));
+	btext_drawchar(hex_asc_lo(v >> 40));
+	btext_drawchar(hex_asc_hi(v >> 32));
+	btext_drawchar(hex_asc_lo(v >> 32));
 #endif
-	btext_drawchar(hex_table[(v >> 28) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 24) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 20) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 16) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >> 12) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >>  8) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >>  4) & 0x0000000FUL]);
-	btext_drawchar(hex_table[(v >>  0) & 0x0000000FUL]);
+	btext_drawchar(hex_asc_hi(v >> 24));
+	btext_drawchar(hex_asc_lo(v >> 24));
+	btext_drawchar(hex_asc_hi(v >> 16));
+	btext_drawchar(hex_asc_lo(v >> 16));
+	btext_drawchar(hex_asc_hi(v >> 8));
+	btext_drawchar(hex_asc_lo(v >> 8));
+	btext_drawchar(hex_asc_hi(v));
+	btext_drawchar(hex_asc_lo(v));
 	btext_drawchar(' ');
 }
 
diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S
index bf118c38575..27f2507279d 100644
--- a/arch/powerpc/kernel/cpu_setup_ppc970.S
+++ b/arch/powerpc/kernel/cpu_setup_ppc970.S
@@ -110,7 +110,7 @@ load_hids:
 	isync
 
 	/* Save away cpu state */
-	LOAD_REG_IMMEDIATE(r5,cpu_state_storage)
+	LOAD_REG_ADDR(r5,cpu_state_storage)
 
 	/* Save HID0,1,4 and 5 */
 	mfspr	r3,SPRN_HID0
@@ -134,7 +134,7 @@ _GLOBAL(__restore_cpu_ppc970)
 	rldicl.	r0,r0,4,63
 	beqlr
 
-	LOAD_REG_IMMEDIATE(r5,cpu_state_storage)
+	LOAD_REG_ADDR(r5,cpu_state_storage)
 	/* Before accessing memory, we make sure rm_ci is clear */
 	li	r0,0
 	mfspr	r3,SPRN_HID4
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 25c273c761d..e70d0483fb4 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -610,6 +610,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750cx,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -623,6 +624,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750cx,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -636,6 +638,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750cx,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -649,6 +652,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -662,6 +666,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -675,6 +680,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -688,6 +694,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -701,6 +708,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750fx,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -714,6 +722,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750fx,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -727,6 +736,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_IBM,
 		.cpu_setup		= __setup_cpu_750,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc750",
@@ -741,6 +751,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_7400,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc7400",
@@ -755,6 +766,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_7400,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc7400",
@@ -769,6 +781,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_7410,
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc7400",
@@ -783,6 +796,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -799,6 +813,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -815,6 +830,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -831,6 +847,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -847,6 +864,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -863,6 +881,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -879,6 +898,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -895,6 +915,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -910,6 +931,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -926,6 +948,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
@@ -942,6 +965,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_G4,
 		.cpu_setup		= __setup_cpu_745x,
 		.oprofile_cpu_type      = "ppc/7450",
 		.oprofile_type		= PPC_OPROFILE_G4,
diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma-iommu.c
index ae5708e3a31..49248f89ce2 100644
--- a/arch/powerpc/kernel/dma_64.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -2,14 +2,10 @@
  * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
  *
  * Provide default implementations of the DMA mapping callbacks for
- * directly mapped busses and busses using the iommu infrastructure
+ * busses using the iommu infrastructure
  */
 
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <asm/bug.h>
 #include <asm/iommu.h>
-#include <asm/abs_addr.h>
 
 /*
  * Generic iommu implementation
@@ -24,7 +20,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 {
 	return iommu_alloc_coherent(dev, dev->archdata.dma_data, size,
 				    dma_handle, device_to_mask(dev), flag,
-				    dev->archdata.numa_node);
+				    dev_to_node(dev));
 }
 
 static void dma_iommu_free_coherent(struct device *dev, size_t size,
@@ -105,96 +101,3 @@ struct dma_mapping_ops dma_iommu_ops = {
 	.dma_supported	= dma_iommu_dma_supported,
 };
 EXPORT_SYMBOL(dma_iommu_ops);
-
-/*
- * Generic direct DMA implementation
- *
- * This implementation supports a per-device offset that can be applied if
- * the address at which memory is visible to devices is not 0. Platform code
- * can set archdata.dma_data to an unsigned long holding the offset. By
- * default the offset is zero.
- */
-
-static unsigned long get_dma_direct_offset(struct device *dev)
-{
-	return (unsigned long)dev->archdata.dma_data;
-}
-
-static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	struct page *page;
-	void *ret;
-	int node = dev->archdata.numa_node;
-
-	page = alloc_pages_node(node, flag, get_order(size));
-	if (page == NULL)
-		return NULL;
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev);
-
-	return ret;
-}
-
-static void dma_direct_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t dma_direct_map_single(struct device *dev, void *ptr,
-					size_t size,
-					enum dma_data_direction direction,
-					struct dma_attrs *attrs)
-{
-	return virt_to_abs(ptr) + get_dma_direct_offset(dev);
-}
-
-static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction,
-				    struct dma_attrs *attrs)
-{
-}
-
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
-			     int nents, enum dma_data_direction direction,
-			     struct dma_attrs *attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev);
-		sg->dma_length = sg->length;
-	}
-
-	return nents;
-}
-
-static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction,
-				struct dma_attrs *attrs)
-{
-}
-
-static int dma_direct_dma_supported(struct device *dev, u64 mask)
-{
-	/* Could be improved to check for memory though it better be
-	 * done via some global so platforms can set the limit in case
-	 * they have limited DMA windows
-	 */
-	return mask >= DMA_32BIT_MASK;
-}
-
-struct dma_mapping_ops dma_direct_ops = {
-	.alloc_coherent	= dma_direct_alloc_coherent,
-	.free_coherent	= dma_direct_free_coherent,
-	.map_single	= dma_direct_map_single,
-	.unmap_single	= dma_direct_unmap_single,
-	.map_sg		= dma_direct_map_sg,
-	.unmap_sg	= dma_direct_unmap_sg,
-	.dma_supported	= dma_direct_dma_supported,
-};
-EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
new file mode 100644
index 00000000000..1562daf8839
--- /dev/null
+++ b/arch/powerpc/kernel/dma.c
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * Provide default implementations of the DMA mapping callbacks for
+ * directly mapped busses.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <asm/bug.h>
+#include <asm/abs_addr.h>
+
+/*
+ * Generic direct DMA implementation
+ *
+ * This implementation supports a per-device offset that can be applied if
+ * the address at which memory is visible to devices is not 0. Platform code
+ * can set archdata.dma_data to an unsigned long holding the offset. By
+ * default the offset is PCI_DRAM_OFFSET.
+ */
+
+static unsigned long get_dma_direct_offset(struct device *dev)
+{
+	if (dev)
+		return (unsigned long)dev->archdata.dma_data;
+
+	return PCI_DRAM_OFFSET;
+}
+
+void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t flag)
+{
+	void *ret;
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	ret = __dma_alloc_coherent(size, dma_handle, flag);
+	if (ret == NULL)
+		return NULL;
+	*dma_handle += get_dma_direct_offset(dev);
+	return ret;
+#else
+	struct page *page;
+	int node = dev_to_node(dev);
+
+	/* ignore region specifiers */
+	flag  &= ~(__GFP_HIGHMEM);
+
+	page = alloc_pages_node(node, flag, get_order(size));
+	if (page == NULL)
+		return NULL;
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev);
+
+	return ret;
+#endif
+}
+
+void dma_direct_free_coherent(struct device *dev, size_t size,
+			      void *vaddr, dma_addr_t dma_handle)
+{
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	__dma_free_coherent(size, vaddr);
+#else
+	free_pages((unsigned long)vaddr, get_order(size));
+#endif
+}
+
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
+			     int nents, enum dma_data_direction direction,
+			     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev);
+		sg->dma_length = sg->length;
+	}
+
+	return nents;
+}
+
+static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction,
+				struct dma_attrs *attrs)
+{
+}
+
+static int dma_direct_dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PPC64
+	/* Could be improved to check for memory though it better be
+	 * done via some global so platforms can set the limit in case
+	 * they have limited DMA windows
+	 */
+	return mask >= DMA_32BIT_MASK;
+#else
+	return 1;
+#endif
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+					     struct page *page,
+					     unsigned long offset,
+					     size_t size,
+					     enum dma_data_direction dir,
+					     struct dma_attrs *attrs)
+{
+	BUG_ON(dir == DMA_NONE);
+	__dma_sync_page(page, offset, size, dir);
+	return page_to_phys(page) + offset + get_dma_direct_offset(dev);
+}
+
+static inline void dma_direct_unmap_page(struct device *dev,
+					 dma_addr_t dma_address,
+					 size_t size,
+					 enum dma_data_direction direction,
+					 struct dma_attrs *attrs)
+{
+}
+
+struct dma_mapping_ops dma_direct_ops = {
+	.alloc_coherent	= dma_direct_alloc_coherent,
+	.free_coherent	= dma_direct_free_coherent,
+	.map_sg		= dma_direct_map_sg,
+	.unmap_sg	= dma_direct_unmap_sg,
+	.dma_supported	= dma_direct_dma_supported,
+	.map_page	= dma_direct_map_page,
+	.unmap_page	= dma_direct_unmap_page,
+};
+EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2d802e97097..fd8b4bae9b0 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -512,31 +512,12 @@ _GLOBAL(ret_from_except_lite)
 #endif
 
 restore:
-	ld	r5,SOFTE(r1)
-#ifdef CONFIG_PPC_ISERIES
 BEGIN_FW_FTR_SECTION
-	cmpdi	0,r5,0
-	beq	4f
-	/* Check for pending interrupts (iSeries) */
-	ld	r3,PACALPPACAPTR(r13)
-	ld	r3,LPPACAANYINT(r3)
-	cmpdi	r3,0
-	beq+	4f			/* skip do_IRQ if no interrupts */
-
-	li	r3,0
-	stb	r3,PACASOFTIRQEN(r13)	/* ensure we are soft-disabled */
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	.trace_hardirqs_off
-	mfmsr	r10
-#endif
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10			/* hard-enable again */
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_IRQ
-	b	.ret_from_except_lite		/* loop back and handle more */
-4:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
+	ld	r5,SOFTE(r1)
+FW_FTR_SECTION_ELSE
+	b	iseries_check_pending_irqs
+ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
+2:
 	TRACE_AND_RESTORE_IRQ(r5);
 
 	/* extract EE bit and use it to restore paca->hard_enabled */
@@ -592,6 +573,30 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 	rfid
 	b	.	/* prevent speculative execution */
 
+iseries_check_pending_irqs:
+#ifdef CONFIG_PPC_ISERIES
+	ld	r5,SOFTE(r1)
+	cmpdi	0,r5,0
+	beq	2b
+	/* Check for pending interrupts (iSeries) */
+	ld	r3,PACALPPACAPTR(r13)
+	ld	r3,LPPACAANYINT(r3)
+	cmpdi	r3,0
+	beq+	2b			/* skip do_IRQ if no interrupts */
+
+	li	r3,0
+	stb	r3,PACASOFTIRQEN(r13)	/* ensure we are soft-disabled */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	.trace_hardirqs_off
+	mfmsr	r10
+#endif
+	ori	r10,r10,MSR_EE
+	mtmsrd	r10			/* hard-enable again */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_IRQ
+	b	.ret_from_except_lite		/* loop back and handle more */
+#endif
+
 do_work:
 #ifdef CONFIG_PREEMPT
 	andi.	r0,r3,MSR_PR	/* Returning to user mode? */
@@ -685,10 +690,6 @@ _GLOBAL(enter_rtas)
 	std	r7,_DAR(r1)
 	mfdsisr	r8
 	std	r8,_DSISR(r1)
-	mfsrr0	r9
-	std	r9,_SRR0(r1)
-	mfsrr1	r10
-	std	r10,_SRR1(r1)
 
 	/* Temporary workaround to clear CR until RTAS can be modified to
 	 * ignore all bits.
@@ -749,6 +750,10 @@ _STATIC(rtas_return_loc)
 	mfspr	r4,SPRN_SPRG3	        /* Get PACA */
 	clrldi	r4,r4,2			/* convert to realmode address */
 
+	bcl	20,31,$+4
+0:	mflr	r3
+	ld	r3,(1f-0b)(r3)		/* get &.rtas_restore_regs */
+
 	mfmsr   r6
 	li	r0,MSR_RI
 	andc	r6,r6,r0
@@ -756,7 +761,6 @@ _STATIC(rtas_return_loc)
 	mtmsrd  r6
         
         ld	r1,PACAR1(r4)           /* Restore our SP */
-	LOAD_REG_IMMEDIATE(r3,.rtas_restore_regs)
         ld	r4,PACASAVEDMSR(r4)     /* Restore our MSR */
 
 	mtspr	SPRN_SRR0,r3
@@ -764,6 +768,9 @@ _STATIC(rtas_return_loc)
 	rfid
 	b	.	/* prevent speculative execution */
 
+	.align	3
+1:	.llong	.rtas_restore_regs
+
 _STATIC(rtas_restore_regs)
 	/* relocation is on at this point */
 	REST_GPR(2, r1)			/* Restore the TOC */
@@ -783,10 +790,6 @@ _STATIC(rtas_restore_regs)
 	mtdar	r7
 	ld	r8,_DSISR(r1)
 	mtdsisr	r8
-	ld	r9,_SRR0(r1)
-	mtsrr0	r9
-	ld	r10,_SRR1(r1)
-	mtsrr1	r10
 
         addi	r1,r1,RTAS_FRAME_SIZE	/* Unstack our frame */
 	ld	r0,16(r1)		/* get return address */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 8bb65751929..0c326823c6d 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -110,6 +110,12 @@ __start:
 #ifdef CONFIG_PPC_MULTIPLATFORM
 	cmpwi	0,r5,0
 	beq	1f
+
+	/* find out where we are now */
+	bcl	20,31,$+4
+0:	mflr	r8			/* r8 = runtime addr here */
+	addis	r8,r8,(_stext - 0b)@ha
+	addi	r8,r8,(_stext - 0b)@l	/* current runtime base addr */
 	bl	prom_init
 	trap
 #endif
@@ -369,13 +375,13 @@ i##n:								\
 DataAccess:
 	EXCEPTION_PROLOG
 	mfspr	r10,SPRN_DSISR
+	stw	r10,_DSISR(r11)
 	andis.	r0,r10,0xa470		/* weird error? */
 	bne	1f			/* if not, try to put a PTE */
 	mfspr	r4,SPRN_DAR		/* into the hash table */
 	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
-1:	stw	r10,_DSISR(r11)
-	mr	r5,r10
+1:	lwz	r5,_DSISR(r11)		/* get DSISR value */
 	mfspr	r4,SPRN_DAR
 	EXC_XFER_EE_LITE(0x300, handle_page_fault)
 
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index cc8fb474d52..84856bee33a 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -82,7 +82,11 @@ END_FTR_SECTION(0, 1)
 	/* Catch branch to 0 in real mode */
 	trap
 
-	/* Secondary processors spin on this value until it goes to 1. */
+	/* Secondary processors spin on this value until it becomes nonzero.
+	 * When it does it contains the real address of the descriptor
+	 * of the function that the cpu should jump to to continue
+	 * initialization.
+	 */
 	.globl  __secondary_hold_spinloop
 __secondary_hold_spinloop:
 	.llong	0x0
@@ -109,8 +113,11 @@ __secondary_hold_acknowledge:
  * before the bulk of the kernel has been relocated.  This code
  * is relocated to physical address 0x60 before prom_init is run.
  * All of it must fit below the first exception vector at 0x100.
+ * Use .globl here not _GLOBAL because we want __secondary_hold
+ * to be the actual text address, not a descriptor.
  */
-_GLOBAL(__secondary_hold)
+	.globl	__secondary_hold
+__secondary_hold:
 	mfmsr	r24
 	ori	r24,r24,MSR_RI
 	mtmsrd	r24			/* RI on */
@@ -121,16 +128,16 @@ _GLOBAL(__secondary_hold)
 	/* Tell the master cpu we're here */
 	/* Relocation is off & we are located at an address less */
 	/* than 0x100, so only need to grab low order offset.    */
-	std	r24,__secondary_hold_acknowledge@l(0)
+	std	r24,__secondary_hold_acknowledge-_stext(0)
 	sync
 
 	/* All secondary cpus wait here until told to start. */
-100:	ld	r4,__secondary_hold_spinloop@l(0)
-	cmpdi	0,r4,1
-	bne	100b
+100:	ld	r4,__secondary_hold_spinloop-_stext(0)
+	cmpdi	0,r4,0
+	beq	100b
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
-	LOAD_REG_IMMEDIATE(r4, .generic_secondary_smp_init)
+	ld	r4,0(r4)		/* deref function descriptor */
 	mtctr	r4
 	mr	r3,r24
 	bctr
@@ -147,6 +154,10 @@ exception_marker:
 /*
  * This is the start of the interrupt handlers for pSeries
  * This code runs with relocation off.
+ * Code from here to __end_interrupts gets copied down to real
+ * address 0x100 when we are running a relocatable kernel.
+ * Therefore any relative branches in this section must only
+ * branch to labels in this section.
  */
 	. = 0x100
 	.globl __start_interrupts
@@ -200,7 +211,20 @@ data_access_slb_pSeries:
 	mfspr	r10,SPRN_SPRG1
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	b	.slb_miss_realmode	/* Rel. branch works in real mode */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	/*
+	 * We can't just use a direct branch to .slb_miss_realmode
+	 * because the distance from here to there depends on where
+	 * the kernel ends up being put.
+	 */
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
 
 	STD_EXCEPTION_PSERIES(0x400, instruction_access)
 
@@ -225,7 +249,15 @@ instruction_access_slb_pSeries:
 	mfspr	r10,SPRN_SPRG1
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	b	.slb_miss_realmode	/* Rel. branch works in real mode */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
 
 	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt)
 	STD_EXCEPTION_PSERIES(0x600, alignment)
@@ -244,14 +276,12 @@ BEGIN_FTR_SECTION
 	beq-	1f
 END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	mr	r9,r13
-	mfmsr	r10
 	mfspr	r13,SPRN_SPRG3
 	mfspr	r11,SPRN_SRR0
-	clrrdi	r12,r13,32
-	oris	r12,r12,system_call_common@h
-	ori	r12,r12,system_call_common@l
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	LOAD_HANDLER(r12, system_call_entry)
 	mtspr	SPRN_SRR0,r12
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
 	mfspr	r12,SPRN_SRR1
 	mtspr	SPRN_SRR1,r10
 	rfid
@@ -325,16 +355,32 @@ do_stab_bolted_pSeries:
 	mfspr	r12,SPRN_SPRG2
 	EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted)
 
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Vectors for the FWNMI option.  Share common code.
+ */
+	.globl system_reset_fwnmi
+      .align 7
+system_reset_fwnmi:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
+
+	.globl machine_check_fwnmi
+      .align 7
+machine_check_fwnmi:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+#endif /* CONFIG_PPC_PSERIES */
+
+#ifdef __DISABLED__
 /*
- * We have some room here  we use that to put
- * the peries slb miss user trampoline code so it's reasonably
- * away from slb_miss_user_common to avoid problems with rfid
- *
  * This is used for when the SLB miss handler has to go virtual,
  * which doesn't happen for now anymore but will once we re-implement
  * dynamic VSIDs for shared page tables
  */
-#ifdef __DISABLED__
 slb_miss_user_pseries:
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	std	r11,PACA_EXGEN+EX_R11(r13)
@@ -357,25 +403,17 @@ slb_miss_user_pseries:
 	b	.				/* prevent spec. execution */
 #endif /* __DISABLED__ */
 
-#ifdef CONFIG_PPC_PSERIES
+	.align	7
+	.globl	__end_interrupts
+__end_interrupts:
+
 /*
- * Vectors for the FWNMI option.  Share common code.
+ * Code from here down to __end_handlers is invoked from the
+ * exception prologs above.  Because the prologs assemble the
+ * addresses of these handlers using the LOAD_HANDLER macro,
+ * which uses an addi instruction, these handlers must be in
+ * the first 32k of the kernel image.
  */
-	.globl system_reset_fwnmi
-      .align 7
-system_reset_fwnmi:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXGEN, system_reset_common)
-
-	.globl machine_check_fwnmi
-      .align 7
-machine_check_fwnmi:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXMC, machine_check_common)
-
-#endif /* CONFIG_PPC_PSERIES */
 
 /*** Common interrupt handlers ***/
 
@@ -414,6 +452,10 @@ machine_check_common:
 	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
 #endif /* CONFIG_CBE_RAS */
 
+	.align	7
+system_call_entry:
+	b	system_call_common
+
 /*
  * Here we have detected that the kernel stack pointer is bad.
  * R9 contains the saved CR, r13 points to the paca,
@@ -457,65 +499,6 @@ bad_stack:
 	b	1b
 
 /*
- * Return from an exception with minimal checks.
- * The caller is assumed to have done EXCEPTION_PROLOG_COMMON.
- * If interrupts have been enabled, or anything has been
- * done that might have changed the scheduling status of
- * any task or sent any task a signal, you should use
- * ret_from_except or ret_from_except_lite instead of this.
- */
-fast_exc_return_irq:			/* restores irq state too */
-	ld	r3,SOFTE(r1)
-	TRACE_AND_RESTORE_IRQ(r3);
-	ld	r12,_MSR(r1)
-	rldicl	r4,r12,49,63		/* get MSR_EE to LSB */
-	stb	r4,PACAHARDIRQEN(r13)	/* restore paca->hard_enabled */
-	b	1f
-
-	.globl	fast_exception_return
-fast_exception_return:
-	ld	r12,_MSR(r1)
-1:	ld	r11,_NIP(r1)
-	andi.	r3,r12,MSR_RI		/* check if RI is set */
-	beq-	unrecov_fer
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	andi.	r3,r12,MSR_PR
-	beq	2f
-	ACCOUNT_CPU_USER_EXIT(r3, r4)
-2:
-#endif
-
-	ld	r3,_CCR(r1)
-	ld	r4,_LINK(r1)
-	ld	r5,_CTR(r1)
-	ld	r6,_XER(r1)
-	mtcr	r3
-	mtlr	r4
-	mtctr	r5
-	mtxer	r6
-	REST_GPR(0, r1)
-	REST_8GPRS(2, r1)
-
-	mfmsr	r10
-	rldicl	r10,r10,48,1		/* clear EE */
-	rldicr	r10,r10,16,61		/* clear RI (LE is 0 already) */
-	mtmsrd	r10,1
-
-	mtspr	SPRN_SRR1,r12
-	mtspr	SPRN_SRR0,r11
-	REST_4GPRS(10, r1)
-	ld	r1,GPR1(r1)
-	rfid
-	b	.	/* prevent speculative execution */
-
-unrecov_fer:
-	bl	.save_nvgprs
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
-	b	1b
-
-/*
  * Here r13 points to the paca, r9 contains the saved CR,
  * SRR0 and SRR1 are saved in r11 and r12,
  * r9 - r13 are saved in paca->exgen.
@@ -616,6 +599,9 @@ unrecov_user_slb:
  */
 _GLOBAL(slb_miss_realmode)
 	mflr	r10
+#ifdef CONFIG_RELOCATABLE
+	mtctr	r11
+#endif
 
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
@@ -666,11 +652,10 @@ BEGIN_FW_FTR_SECTION
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif /* CONFIG_PPC_ISERIES */
 	mfspr	r11,SPRN_SRR0
-	clrrdi	r10,r13,32
+	ld	r10,PACAKBASE(r13)
 	LOAD_HANDLER(r10,unrecov_slb)
 	mtspr	SPRN_SRR0,r10
-	mfmsr	r10
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
+	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
 	rfid
 	b	.
@@ -766,6 +751,85 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	bl	.altivec_unavailable_exception
 	b	.ret_from_except
 
+	.align	7
+	.globl vsx_unavailable_common
+vsx_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	bne	.load_up_vsx
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.vsx_unavailable_exception
+	b	.ret_from_except
+
+	.align	7
+	.globl	__end_handlers
+__end_handlers:
+
+/*
+ * Return from an exception with minimal checks.
+ * The caller is assumed to have done EXCEPTION_PROLOG_COMMON.
+ * If interrupts have been enabled, or anything has been
+ * done that might have changed the scheduling status of
+ * any task or sent any task a signal, you should use
+ * ret_from_except or ret_from_except_lite instead of this.
+ */
+fast_exc_return_irq:			/* restores irq state too */
+	ld	r3,SOFTE(r1)
+	TRACE_AND_RESTORE_IRQ(r3);
+	ld	r12,_MSR(r1)
+	rldicl	r4,r12,49,63		/* get MSR_EE to LSB */
+	stb	r4,PACAHARDIRQEN(r13)	/* restore paca->hard_enabled */
+	b	1f
+
+	.globl	fast_exception_return
+fast_exception_return:
+	ld	r12,_MSR(r1)
+1:	ld	r11,_NIP(r1)
+	andi.	r3,r12,MSR_RI		/* check if RI is set */
+	beq-	unrecov_fer
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	andi.	r3,r12,MSR_PR
+	beq	2f
+	ACCOUNT_CPU_USER_EXIT(r3, r4)
+2:
+#endif
+
+	ld	r3,_CCR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_CTR(r1)
+	ld	r6,_XER(r1)
+	mtcr	r3
+	mtlr	r4
+	mtctr	r5
+	mtxer	r6
+	REST_GPR(0, r1)
+	REST_8GPRS(2, r1)
+
+	mfmsr	r10
+	rldicl	r10,r10,48,1		/* clear EE */
+	rldicr	r10,r10,16,61		/* clear RI (LE is 0 already) */
+	mtmsrd	r10,1
+
+	mtspr	SPRN_SRR1,r12
+	mtspr	SPRN_SRR0,r11
+	REST_4GPRS(10, r1)
+	ld	r1,GPR1(r1)
+	rfid
+	b	.	/* prevent speculative execution */
+
+unrecov_fer:
+	bl	.save_nvgprs
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.unrecoverable_exception
+	b	1b
+
 #ifdef CONFIG_ALTIVEC
 /*
  * load_up_altivec(unused, unused, tsk)
@@ -840,22 +904,6 @@ _STATIC(load_up_altivec)
 	blr
 #endif /* CONFIG_ALTIVEC */
 
-	.align	7
-	.globl vsx_unavailable_common
-vsx_unavailable_common:
-	EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	bne	.load_up_vsx
-1:
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
-	bl	.vsx_unavailable_exception
-	b	.ret_from_except
-
 #ifdef CONFIG_VSX
 /*
  * load_up_vsx(unused, unused, tsk)
@@ -1175,11 +1223,14 @@ _GLOBAL(generic_secondary_smp_init)
 	/* turn on 64-bit mode */
 	bl	.enable_64b_mode
 
+	/* get the TOC pointer (real address) */
+	bl	.relative_toc
+
 	/* Set up a paca value for this processor. Since we have the
 	 * physical cpu id in r24, we need to search the pacas to find
 	 * which logical id maps to our physical one.
 	 */
-	LOAD_REG_IMMEDIATE(r13, paca)	/* Get base vaddr of paca array	 */
+	LOAD_REG_ADDR(r13, paca)	/* Get base vaddr of paca array	 */
 	li	r5,0			/* logical cpu id                */
 1:	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
 	cmpw	r6,r24			/* Compare to our id             */
@@ -1208,7 +1259,7 @@ _GLOBAL(generic_secondary_smp_init)
 	sync				/* order paca.run and cur_cpu_spec */
 
 	/* See if we need to call a cpu state restore handler */
-	LOAD_REG_IMMEDIATE(r23, cur_cpu_spec)
+	LOAD_REG_ADDR(r23, cur_cpu_spec)
 	ld	r23,0(r23)
 	ld	r23,CPU_SPEC_RESTORE(r23)
 	cmpdi	0,r23,0
@@ -1224,10 +1275,15 @@ _GLOBAL(generic_secondary_smp_init)
 	b	__secondary_start
 #endif
 
+/*
+ * Turn the MMU off.
+ * Assumes we're mapped EA == RA if the MMU is on.
+ */
 _STATIC(__mmu_off)
 	mfmsr	r3
 	andi.	r0,r3,MSR_IR|MSR_DR
 	beqlr
+	mflr	r4
 	andc	r3,r3,r0
 	mtspr	SPRN_SRR0,r4
 	mtspr	SPRN_SRR1,r3
@@ -1248,6 +1304,18 @@ _STATIC(__mmu_off)
  *
  */
 _GLOBAL(__start_initialization_multiplatform)
+	/* Make sure we are running in 64 bits mode */
+	bl	.enable_64b_mode
+
+	/* Get TOC pointer (current runtime address) */
+	bl	.relative_toc
+
+	/* find out where we are now */
+	bcl	20,31,$+4
+0:	mflr	r26			/* r26 = runtime addr here */
+	addis	r26,r26,(_stext - 0b)@ha
+	addi	r26,r26,(_stext - 0b)@l	/* current runtime base addr */
+
 	/*
 	 * Are we booted from a PROM Of-type client-interface ?
 	 */
@@ -1259,9 +1327,6 @@ _GLOBAL(__start_initialization_multiplatform)
 	mr	r31,r3
 	mr	r30,r4
 
-	/* Make sure we are running in 64 bits mode */
-	bl	.enable_64b_mode
-
 	/* Setup some critical 970 SPRs before switching MMU off */
 	mfspr	r0,SPRN_PVR
 	srwi	r0,r0,16
@@ -1276,9 +1341,7 @@ _GLOBAL(__start_initialization_multiplatform)
 1:	bl	.__cpu_preinit_ppc970
 2:
 
-	/* Switch off MMU if not already */
-	LOAD_REG_IMMEDIATE(r4, .__after_prom_start - KERNELBASE)
-	add	r4,r4,r30
+	/* Switch off MMU if not already off */
 	bl	.__mmu_off
 	b	.__after_prom_start
 
@@ -1293,22 +1356,15 @@ _INIT_STATIC(__boot_from_prom)
 	/*
 	 * Align the stack to 16-byte boundary
 	 * Depending on the size and layout of the ELF sections in the initial
-	 * boot binary, the stack pointer will be unalignet on PowerMac
+	 * boot binary, the stack pointer may be unaligned on PowerMac
 	 */
 	rldicr	r1,r1,0,59
 
-	/* Make sure we are running in 64 bits mode */
-	bl	.enable_64b_mode
-
-	/* put a relocation offset into r3 */
-	bl	.reloc_offset
-
-	LOAD_REG_IMMEDIATE(r2,__toc_start)
-	addi	r2,r2,0x4000
-	addi	r2,r2,0x4000
-
-	/* Relocate the TOC from a virt addr to a real addr */
-	add	r2,r2,r3
+#ifdef CONFIG_RELOCATABLE
+	/* Relocate code for where we are now */
+	mr	r3,r26
+	bl	.relocate
+#endif
 
 	/* Restore parameters */
 	mr	r3,r31
@@ -1318,60 +1374,51 @@ _INIT_STATIC(__boot_from_prom)
 	mr	r7,r27
 
 	/* Do all of the interaction with OF client interface */
+	mr	r8,r26
 	bl	.prom_init
 	/* We never return */
 	trap
 
 _STATIC(__after_prom_start)
+#ifdef CONFIG_RELOCATABLE
+	/* process relocations for the final address of the kernel */
+	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
+	sldi	r25,r25,32
+	mr	r3,r25
+	bl	.relocate
+#endif
 
 /*
- * We need to run with __start at physical address PHYSICAL_START.
+ * We need to run with _stext at physical address PHYSICAL_START.
  * This will leave some code in the first 256B of
  * real memory, which are reserved for software use.
- * The remainder of the first page is loaded with the fixed
- * interrupt vectors.  The next two pages are filled with
- * unknown exception placeholders.
  *
  * Note: This process overwrites the OF exception vectors.
- *	r26 == relocation offset
- *	r27 == KERNELBASE
  */
-	bl	.reloc_offset
-	mr	r26,r3
-	LOAD_REG_IMMEDIATE(r27, KERNELBASE)
-
-	LOAD_REG_IMMEDIATE(r3, PHYSICAL_START)	/* target addr */
-
-	// XXX FIXME: Use phys returned by OF (r30)
-	add	r4,r27,r26 		/* source addr			 */
-					/* current address of _start	 */
-					/*   i.e. where we are running	 */
-					/*	the source addr		 */
-
-	cmpdi	r4,0			/* In some cases the loader may  */
-	bne	1f
-	b	.start_here_multiplatform /* have already put us at zero */
-					/* so we can skip the copy.      */
-1:	LOAD_REG_IMMEDIATE(r5,copy_to_here) /* # bytes of memory to copy */
-	sub	r5,r5,r27
-
+	li	r3,0			/* target addr */
+	mr.	r4,r26			/* In some cases the loader may  */
+	beq	9f			/* have already put us at zero */
+	lis	r5,(copy_to_here - _stext)@ha
+	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
 
 	bl	.copy_and_flush		/* copy the first n bytes	 */
 					/* this includes the code being	 */
 					/* executed here.		 */
-
-	LOAD_REG_IMMEDIATE(r0, 4f)	/* Jump to the copy of this code */
-	mtctr	r0			/* that we just made/relocated	 */
+	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
+	addi	r8,r8,(4f - _stext)@l	/* that we just made */
+	mtctr	r8
 	bctr
 
-4:	LOAD_REG_IMMEDIATE(r5,klimit)
-	add	r5,r5,r26
-	ld	r5,0(r5)		/* get the value of klimit */
-	sub	r5,r5,r27
+4:	/* Now copy the rest of the kernel up to _end */
+	addis	r5,r26,(p_end - _stext)@ha
+	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
 	bl	.copy_and_flush		/* copy the rest */
-	b	.start_here_multiplatform
+
+9:	b	.start_here_multiplatform
+
+p_end:	.llong	_end - _stext
 
 /*
  * Copy routine used to copy the kernel to start at physical address 0
@@ -1436,6 +1483,9 @@ _GLOBAL(pmac_secondary_start)
 	/* turn on 64-bit mode */
 	bl	.enable_64b_mode
 
+	/* get TOC pointer (real address) */
+	bl	.relative_toc
+
 	/* Copy some CPU settings from CPU 0 */
 	bl	.__restore_cpu_ppc970
 
@@ -1445,10 +1495,10 @@ _GLOBAL(pmac_secondary_start)
 	mtmsrd	r3			/* RI on */
 
 	/* Set up a paca value for this processor. */
-	LOAD_REG_IMMEDIATE(r4, paca)	/* Get base vaddr of paca array	*/
-	mulli	r13,r24,PACA_SIZE	 /* Calculate vaddr of right paca */
+	LOAD_REG_ADDR(r4,paca)		/* Get base vaddr of paca array	*/
+	mulli	r13,r24,PACA_SIZE	/* Calculate vaddr of right paca */
 	add	r13,r13,r4		/* for this processor.		*/
-	mtspr	SPRN_SPRG3,r13		 /* Save vaddr of paca in SPRG3	*/
+	mtspr	SPRN_SPRG3,r13		/* Save vaddr of paca in SPRG3	*/
 
 	/* Create a temp kernel stack for use before relocation is on.	*/
 	ld	r1,PACAEMERGSP(r13)
@@ -1476,9 +1526,6 @@ __secondary_start:
 	/* Set thread priority to MEDIUM */
 	HMT_MEDIUM
 
-	/* Load TOC */
-	ld	r2,PACATOC(r13)
-
 	/* Do early setup for that CPU (stab, slb, hash table pointer) */
 	bl	.early_setup_secondary
 
@@ -1515,9 +1562,11 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
 /* 
  * Running with relocation on at this point.  All we want to do is
- * zero the stack back-chain pointer before going into C code.
+ * zero the stack back-chain pointer and get the TOC virtual address
+ * before going into C code.
  */
 _GLOBAL(start_secondary_prolog)
+	ld	r2,PACATOC(r13)
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
 	bl	.start_secondary
@@ -1529,34 +1578,46 @@ _GLOBAL(start_secondary_prolog)
  */
 _GLOBAL(enable_64b_mode)
 	mfmsr	r11			/* grab the current MSR */
-	li	r12,1
-	rldicr	r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
-	or	r11,r11,r12
-	li	r12,1
-	rldicr	r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
+	li	r12,(MSR_SF | MSR_ISF)@highest
+	sldi	r12,r12,48
 	or	r11,r11,r12
 	mtmsrd	r11
 	isync
 	blr
 
 /*
+ * This puts the TOC pointer into r2, offset by 0x8000 (as expected
+ * by the toolchain).  It computes the correct value for wherever we
+ * are running at the moment, using position-independent code.
+ */
+_GLOBAL(relative_toc)
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r9
+	ld	r2,(p_toc - 0b)(r9)
+	add	r2,r2,r9
+	mtlr	r0
+	blr
+
+p_toc:	.llong	__toc_start + 0x8000 - 0b
+
+/*
  * This is where the main kernel code starts.
  */
 _INIT_STATIC(start_here_multiplatform)
-	/* get a new offset, now that the kernel has moved. */
-	bl	.reloc_offset
-	mr	r26,r3
+	/* set up the TOC (real address) */
+	bl	.relative_toc
 
 	/* Clear out the BSS. It may have been done in prom_init,
 	 * already but that's irrelevant since prom_init will soon
 	 * be detached from the kernel completely. Besides, we need
 	 * to clear it now for kexec-style entry.
 	 */
-	LOAD_REG_IMMEDIATE(r11,__bss_stop)
-	LOAD_REG_IMMEDIATE(r8,__bss_start)
+	LOAD_REG_ADDR(r11,__bss_stop)
+	LOAD_REG_ADDR(r8,__bss_start)
 	sub	r11,r11,r8		/* bss size			*/
 	addi	r11,r11,7		/* round up to an even double word */
-	rldicl. r11,r11,61,3		/* shift right by 3		*/
+	srdi.	r11,r11,3		/* shift right by 3		*/
 	beq	4f
 	addi	r8,r8,-8
 	li	r0,0
@@ -1569,35 +1630,35 @@ _INIT_STATIC(start_here_multiplatform)
 	ori	r6,r6,MSR_RI
 	mtmsrd	r6			/* RI on */
 
-	/* The following gets the stack and TOC set up with the regs */
+#ifdef CONFIG_RELOCATABLE
+	/* Save the physical address we're running at in kernstart_addr */
+	LOAD_REG_ADDR(r4, kernstart_addr)
+	clrldi	r0,r25,2
+	std	r0,0(r4)
+#endif
+
+	/* The following gets the stack set up with the regs */
 	/* pointing to the real addr of the kernel stack.  This is   */
 	/* all done to support the C function call below which sets  */
 	/* up the htab.  This is done because we have relocated the  */
 	/* kernel but are still running in real mode. */
 
-	LOAD_REG_IMMEDIATE(r3,init_thread_union)
-	add	r3,r3,r26
+	LOAD_REG_ADDR(r3,init_thread_union)
 
-	/* set up a stack pointer (physical address) */
+	/* set up a stack pointer */
 	addi	r1,r3,THREAD_SIZE
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 
-	/* set up the TOC (physical address) */
-	LOAD_REG_IMMEDIATE(r2,__toc_start)
-	addi	r2,r2,0x4000
-	addi	r2,r2,0x4000
-	add	r2,r2,r26
-
 	/* Do very early kernel initializations, including initial hash table,
 	 * stab and slb setup before we turn on relocation.	*/
 
 	/* Restore parameters passed from prom_init/kexec */
 	mr	r3,r31
- 	bl	.early_setup
+	bl	.early_setup		/* also sets r13 and SPRG3 */
 
-	LOAD_REG_IMMEDIATE(r3, .start_here_common)
-	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
+	LOAD_REG_ADDR(r3, .start_here_common)
+	ld	r4,PACAKMSR(r13)
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
 	rfid
@@ -1606,20 +1667,10 @@ _INIT_STATIC(start_here_multiplatform)
 	/* This is where all platforms converge execution */
 _INIT_GLOBAL(start_here_common)
 	/* relocation is on at this point */
+	std	r1,PACAKSAVE(r13)
 
-	/* The following code sets up the SP and TOC now that we are */
-	/* running with translation enabled. */
-
-	LOAD_REG_IMMEDIATE(r3,init_thread_union)
-
-	/* set up the stack */
-	addi	r1,r3,THREAD_SIZE
-	li	r0,0
-	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
-
-	/* Load the TOC */
+	/* Load the TOC (virtual address) */
 	ld	r2,PACATOC(r13)
-	std	r1,PACAKSAVE(r13)
 
 	bl	.setup_system
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 3cb52fa0eda..590304c24da 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -422,7 +422,6 @@ skpinv:	addi	r6,r6,1				/* Increment */
  *   r12 is pointer to the pte
  */
 #ifdef CONFIG_PTE_64BIT
-#define PTE_FLAGS_OFFSET	4
 #define FIND_PTE	\
 	rlwinm	r12, r10, 13, 19, 29;	/* Compute pgdir/pmd offset */	\
 	lwzx	r11, r12, r11;		/* Get pgd/pmd entry */		\
@@ -431,7 +430,6 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	rlwimi	r12, r10, 23, 20, 28;	/* Compute pte address */	\
 	lwz	r11, 4(r12);		/* Get pte entry */
 #else
-#define PTE_FLAGS_OFFSET	0
 #define FIND_PTE	\
 	rlwimi	r11, r10, 12, 20, 29;	/* Create L1 (pgdir/pmd) address */	\
 	lwz	r11, 0(r11);		/* Get L1 entry */			\
@@ -579,13 +577,19 @@ interrupt_base:
 
 	FIND_PTE
 	andc.	r13,r13,r11		/* Check permission */
-	bne	2f			/* Bail if permission mismach */
 
 #ifdef CONFIG_PTE_64BIT
-	lwz	r13, 0(r12)
+#ifdef CONFIG_SMP
+	subf	r10,r11,r12		/* create false data dep */
+	lwzx	r13,r11,r10		/* Get upper pte bits */
+#else
+	lwz	r13,0(r12)		/* Get upper pte bits */
+#endif
 #endif
 
-	 /* Jump to common tlb load */
+	bne	2f			/* Bail if permission/valid mismach */
+
+	/* Jump to common tlb load */
 	b	finish_tlb_load
 2:
 	/* The bailout.  Restore registers to pre-exception conditions
@@ -640,12 +644,18 @@ interrupt_base:
 
 	FIND_PTE
 	andc.	r13,r13,r11		/* Check permission */
-	bne	2f			/* Bail if permission mismach */
 
 #ifdef CONFIG_PTE_64BIT
-	lwz	r13, 0(r12)
+#ifdef CONFIG_SMP
+	subf	r10,r11,r12		/* create false data dep */
+	lwzx	r13,r11,r10		/* Get upper pte bits */
+#else
+	lwz	r13,0(r12)		/* Get upper pte bits */
+#endif
 #endif
 
+	bne	2f			/* Bail if permission mismach */
+
 	/* Jump to common TLB load point */
 	b	finish_tlb_load
 
@@ -702,7 +712,7 @@ interrupt_base:
 /*
  * Both the instruction and data TLB miss get to this
  * point to load the TLB.
- *	r10 - EA of fault
+ *	r10 - available to use
  *	r11 - TLB (info from Linux PTE)
  *	r12 - available to use
  *	r13 - upper bits of PTE (if PTE_64BIT) or available to use
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 550a19399bf..ea1ba89f9c9 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -51,17 +51,6 @@ static int protect4gb = 1;
 
 static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);
 
-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_protect4gb(char *str)
 {
 	if (strcmp(str, "on") == 0)
@@ -325,7 +314,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		}
 		/* Allocate iommu entries for that segment */
 		vaddr = (unsigned long) sg_virt(s);
-		npages = iommu_num_pages(vaddr, slen);
+		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE);
 		align = 0;
 		if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE &&
 		    (vaddr & ~PAGE_MASK) == 0)
@@ -418,7 +407,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			unsigned long vaddr, npages;
 
 			vaddr = s->dma_address & IOMMU_PAGE_MASK;
-			npages = iommu_num_pages(s->dma_address, s->dma_length);
+			npages = iommu_num_pages(s->dma_address, s->dma_length,
+						 IOMMU_PAGE_SIZE);
 			__iommu_free(tbl, vaddr, npages);
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
@@ -452,7 +442,8 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 		if (sg->dma_length == 0)
 			break;
-		npages = iommu_num_pages(dma_handle, sg->dma_length);
+		npages = iommu_num_pages(dma_handle, sg->dma_length,
+					 IOMMU_PAGE_SIZE);
 		__iommu_free(tbl, dma_handle, npages);
 		sg = sg_next(sg);
 	}
@@ -584,7 +575,7 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl,
 	BUG_ON(direction == DMA_NONE);
 
 	uaddr = (unsigned long)vaddr;
-	npages = iommu_num_pages(uaddr, size);
+	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE);
 
 	if (tbl) {
 		align = 0;
@@ -617,7 +608,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
 	BUG_ON(direction == DMA_NONE);
 
 	if (tbl) {
-		npages = iommu_num_pages(dma_handle, size);
+		npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE);
 		iommu_free(tbl, dma_handle, npages);
 	}
 }
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index d972decf032..ac222d0ab12 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -439,8 +439,8 @@ void do_softirq(void)
 
 static LIST_HEAD(irq_hosts);
 static DEFINE_SPINLOCK(irq_big_lock);
-static DEFINE_PER_CPU(unsigned int, irq_radix_reader);
-static unsigned int irq_radix_writer;
+static unsigned int revmap_trees_allocated;
+static DEFINE_MUTEX(revmap_trees_mutex);
 struct irq_map_entry irq_map[NR_IRQS];
 static unsigned int irq_virq_count = NR_IRQS;
 static struct irq_host *irq_default_host;
@@ -583,57 +583,6 @@ void irq_set_virq_count(unsigned int count)
 		irq_virq_count = count;
 }
 
-/* radix tree not lockless safe ! we use a brlock-type mecanism
- * for now, until we can use a lockless radix tree
- */
-static void irq_radix_wrlock(unsigned long *flags)
-{
-	unsigned int cpu, ok;
-
-	spin_lock_irqsave(&irq_big_lock, *flags);
-	irq_radix_writer = 1;
-	smp_mb();
-	do {
-		barrier();
-		ok = 1;
-		for_each_possible_cpu(cpu) {
-			if (per_cpu(irq_radix_reader, cpu)) {
-				ok = 0;
-				break;
-			}
-		}
-		if (!ok)
-			cpu_relax();
-	} while(!ok);
-}
-
-static void irq_radix_wrunlock(unsigned long flags)
-{
-	smp_wmb();
-	irq_radix_writer = 0;
-	spin_unlock_irqrestore(&irq_big_lock, flags);
-}
-
-static void irq_radix_rdlock(unsigned long *flags)
-{
-	local_irq_save(*flags);
-	__get_cpu_var(irq_radix_reader) = 1;
-	smp_mb();
-	if (likely(irq_radix_writer == 0))
-		return;
-	__get_cpu_var(irq_radix_reader) = 0;
-	smp_wmb();
-	spin_lock(&irq_big_lock);
-	__get_cpu_var(irq_radix_reader) = 1;
-	spin_unlock(&irq_big_lock);
-}
-
-static void irq_radix_rdunlock(unsigned long flags)
-{
-	__get_cpu_var(irq_radix_reader) = 0;
-	local_irq_restore(flags);
-}
-
 static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 			    irq_hw_number_t hwirq)
 {
@@ -788,7 +737,6 @@ void irq_dispose_mapping(unsigned int virq)
 {
 	struct irq_host *host;
 	irq_hw_number_t hwirq;
-	unsigned long flags;
 
 	if (virq == NO_IRQ)
 		return;
@@ -821,12 +769,16 @@ void irq_dispose_mapping(unsigned int virq)
 			host->revmap_data.linear.revmap[hwirq] = NO_IRQ;
 		break;
 	case IRQ_HOST_MAP_TREE:
-		/* Check if radix tree allocated yet */
-		if (host->revmap_data.tree.gfp_mask == 0)
+		/*
+		 * Check if radix tree allocated yet, if not then nothing to
+		 * remove.
+		 */
+		smp_rmb();
+		if (revmap_trees_allocated < 1)
 			break;
-		irq_radix_wrlock(&flags);
+		mutex_lock(&revmap_trees_mutex);
 		radix_tree_delete(&host->revmap_data.tree, hwirq);
-		irq_radix_wrunlock(flags);
+		mutex_unlock(&revmap_trees_mutex);
 		break;
 	}
 
@@ -875,43 +827,62 @@ unsigned int irq_find_mapping(struct irq_host *host,
 EXPORT_SYMBOL_GPL(irq_find_mapping);
 
 
-unsigned int irq_radix_revmap(struct irq_host *host,
-			      irq_hw_number_t hwirq)
+unsigned int irq_radix_revmap_lookup(struct irq_host *host,
+				     irq_hw_number_t hwirq)
 {
-	struct radix_tree_root *tree;
 	struct irq_map_entry *ptr;
 	unsigned int virq;
-	unsigned long flags;
 
 	WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE);
 
-	/* Check if the radix tree exist yet. We test the value of
-	 * the gfp_mask for that. Sneaky but saves another int in the
-	 * structure. If not, we fallback to slow mode
+	/*
+	 * Check if the radix tree exists and has bee initialized.
+	 * If not, we fallback to slow mode
 	 */
-	tree = &host->revmap_data.tree;
-	if (tree->gfp_mask == 0)
+	if (revmap_trees_allocated < 2)
 		return irq_find_mapping(host, hwirq);
 
 	/* Now try to resolve */
-	irq_radix_rdlock(&flags);
-	ptr = radix_tree_lookup(tree, hwirq);
-	irq_radix_rdunlock(flags);
+	/*
+	 * No rcu_read_lock(ing) needed, the ptr returned can't go under us
+	 * as it's referencing an entry in the static irq_map table.
+	 */
+	ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq);
 
-	/* Found it, return */
-	if (ptr) {
+	/*
+	 * If found in radix tree, then fine.
+	 * Else fallback to linear lookup - this should not happen in practice
+	 * as it means that we failed to insert the node in the radix tree.
+	 */
+	if (ptr)
 		virq = ptr - irq_map;
-		return virq;
-	}
+	else
+		virq = irq_find_mapping(host, hwirq);
+
+	return virq;
+}
+
+void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
+			     irq_hw_number_t hwirq)
+{
+
+	WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE);
+
+	/*
+	 * Check if the radix tree exists yet.
+	 * If not, then the irq will be inserted into the tree when it gets
+	 * initialized.
+	 */
+	smp_rmb();
+	if (revmap_trees_allocated < 1)
+		return;
 
-	/* If not there, try to insert it */
-	virq = irq_find_mapping(host, hwirq);
 	if (virq != NO_IRQ) {
-		irq_radix_wrlock(&flags);
-		radix_tree_insert(tree, hwirq, &irq_map[virq]);
-		irq_radix_wrunlock(flags);
+		mutex_lock(&revmap_trees_mutex);
+		radix_tree_insert(&host->revmap_data.tree, hwirq,
+				  &irq_map[virq]);
+		mutex_unlock(&revmap_trees_mutex);
 	}
-	return virq;
 }
 
 unsigned int irq_linear_revmap(struct irq_host *host,
@@ -1020,14 +991,44 @@ void irq_early_init(void)
 static int irq_late_init(void)
 {
 	struct irq_host *h;
-	unsigned long flags;
+	unsigned int i;
 
-	irq_radix_wrlock(&flags);
+	/*
+	 * No mutual exclusion with respect to accessors of the tree is needed
+	 * here as the synchronization is done via the state variable
+	 * revmap_trees_allocated.
+	 */
 	list_for_each_entry(h, &irq_hosts, link) {
 		if (h->revmap_type == IRQ_HOST_MAP_TREE)
-			INIT_RADIX_TREE(&h->revmap_data.tree, GFP_ATOMIC);
+			INIT_RADIX_TREE(&h->revmap_data.tree, GFP_KERNEL);
+	}
+
+	/*
+	 * Make sure the radix trees inits are visible before setting
+	 * the flag
+	 */
+	smp_wmb();
+	revmap_trees_allocated = 1;
+
+	/*
+	 * Insert the reverse mapping for those interrupts already present
+	 * in irq_map[].
+	 */
+	mutex_lock(&revmap_trees_mutex);
+	for (i = 0; i < irq_virq_count; i++) {
+		if (irq_map[i].host &&
+		    (irq_map[i].host->revmap_type == IRQ_HOST_MAP_TREE))
+			radix_tree_insert(&irq_map[i].host->revmap_data.tree,
+					  irq_map[i].hwirq, &irq_map[i]);
 	}
-	irq_radix_wrunlock(flags);
+	mutex_unlock(&revmap_trees_mutex);
+
+	/*
+	 * Make sure the radix trees insertions are visible before setting
+	 * the flag
+	 */
+	smp_wmb();
+	revmap_trees_allocated = 2;
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index b3eef30b513..d051e8cbcd0 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -510,10 +510,10 @@ static ssize_t update_ppp(u64 *entitlement, u8 *weight)
 		return -EINVAL;
 
 	pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
-	         __FUNCTION__, ppp_data.entitlement, ppp_data.weight);
+		 __func__, ppp_data.entitlement, ppp_data.weight);
 
 	pr_debug("%s: new_entitled = %lu, new_weight = %u\n",
-		 __FUNCTION__, new_entitled, new_weight);
+		 __func__, new_entitled, new_weight);
 
 	retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight);
 	return retval;
@@ -556,10 +556,10 @@ static ssize_t update_mpp(u64 *entitlement, u8 *weight)
 		return -EINVAL;
 
 	pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
-	         __FUNCTION__, mpp_data.entitled_mem, mpp_data.mem_weight);
+	         __func__, mpp_data.entitled_mem, mpp_data.mem_weight);
 
 	pr_debug("%s: new_entitled = %lu, new_weight = %u\n",
-	         __FUNCTION__, new_entitled, new_weight);
+		 __func__, new_entitled, new_weight);
 
 	rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight);
 	return rc;
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 85cb6f34084..2d29752cbe1 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -31,11 +31,14 @@ _GLOBAL(reloc_offset)
 	mflr	r0
 	bl	1f
 1:	mflr	r3
-	LOAD_REG_IMMEDIATE(r4,1b)
+	PPC_LL	r4,(2f-1b)(r3)
 	subf	r3,r4,r3
 	mtlr	r0
 	blr
 
+	.align	3
+2:	PPC_LONG 1b
+
 /*
  * add_reloc_offset(x) returns x + reloc_offset().
  */
@@ -43,12 +46,15 @@ _GLOBAL(add_reloc_offset)
 	mflr	r0
 	bl	1f
 1:	mflr	r5
-	LOAD_REG_IMMEDIATE(r4,1b)
+	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
 	add	r3,r3,r5
 	mtlr	r0
 	blr
 
+	.align	3
+2:	PPC_LONG 1b
+
 _GLOBAL(kernel_execve)
 	li	r0,__NR_execve
 	sc
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7a6dfbca768..6a9b4bf0d17 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -274,6 +274,10 @@ _GLOBAL(real_writeb)
 /*
  * Flush MMU TLB
  */
+#ifndef CONFIG_FSL_BOOKE
+_GLOBAL(_tlbil_all)
+_GLOBAL(_tlbil_pid)
+#endif
 _GLOBAL(_tlbia)
 #if defined(CONFIG_40x)
 	sync			/* Flush to memory before changing mapping */
@@ -344,6 +348,9 @@ _GLOBAL(_tlbia)
 /*
  * Flush MMU TLB for a particular address
  */
+#ifndef CONFIG_FSL_BOOKE
+_GLOBAL(_tlbil_va)
+#endif
 _GLOBAL(_tlbie)
 #if defined(CONFIG_40x)
 	/* We run the search with interrupts disabled because we have to change
@@ -436,6 +443,53 @@ _GLOBAL(_tlbie)
 #endif /* ! CONFIG_40x */
 	blr
 
+#if defined(CONFIG_FSL_BOOKE)
+/*
+ * Flush MMU TLB, but only on the local processor (no broadcast)
+ */
+_GLOBAL(_tlbil_all)
+#define MMUCSR0_TLBFI	(MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
+			 MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
+	li	r3,(MMUCSR0_TLBFI)@l
+	mtspr	SPRN_MMUCSR0, r3
+1:
+	mfspr	r3,SPRN_MMUCSR0
+	andi.	r3,r3,MMUCSR0_TLBFI@l
+	bne	1b
+	blr
+
+/*
+ * Flush MMU TLB for a particular process id, but only on the local processor
+ * (no broadcast)
+ */
+_GLOBAL(_tlbil_pid)
+/* we currently do an invalidate all since we don't have per pid invalidate */
+	li	r3,(MMUCSR0_TLBFI)@l
+	mtspr	SPRN_MMUCSR0, r3
+1:
+	mfspr	r3,SPRN_MMUCSR0
+	andi.	r3,r3,MMUCSR0_TLBFI@l
+	bne	1b
+	blr
+
+/*
+ * Flush MMU TLB for a particular address, but only on the local processor
+ * (no broadcast)
+ */
+_GLOBAL(_tlbil_va)
+	slwi	r4,r4,16
+	mtspr	SPRN_MAS6,r4		/* assume AS=0 for now */
+	tlbsx	0,r3
+	mfspr	r4,SPRN_MAS1		/* check valid */
+	andis.	r3,r4,MAS1_VALID@h
+	beqlr
+	rlwinm	r4,r4,0,1,31
+	mtspr	SPRN_MAS1,r4
+	tlbwe
+	blr
+#endif /* CONFIG_FSL_BOOKE */
+
+
 /*
  * Flush instruction cache.
  * This is a no-op on the 601.
@@ -846,8 +900,10 @@ _GLOBAL(kernel_thread)
 	li	r4,0		/* new sp (unused) */
 	li	r0,__NR_clone
 	sc
-	cmpwi	0,r3,0		/* parent or child? */
-	bne	1f		/* return if parent */
+	bns+	1f		/* did system call indicate error? */
+	neg	r3,r3		/* if so, make return code negative */
+1:	cmpwi	0,r3,0		/* parent or child? */
+	bne	2f		/* return if parent */
 	li	r0,0		/* make top-level stack frame */
 	stwu	r0,-16(r1)
 	mtlr	r30		/* fn addr in lr */
@@ -857,7 +913,7 @@ _GLOBAL(kernel_thread)
 	li	r0,__NR_exit	/* exit if function returns */
 	li	r3,0
 	sc
-1:	lwz	r30,8(r1)
+2:	lwz	r30,8(r1)
 	lwz	r31,12(r1)
 	addi	r1,r1,16
 	blr
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4dd70cf7bb4..3053fe5c62f 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -426,8 +426,10 @@ _GLOBAL(kernel_thread)
 	li	r4,0		/* new sp (unused) */
 	li	r0,__NR_clone
 	sc
-	cmpdi	0,r3,0		/* parent or child? */
-	bne	1f		/* return if parent */
+	bns+	1f		/* did system call indicate error? */
+	neg	r3,r3		/* if so, make return code negative */
+1:	cmpdi	0,r3,0		/* parent or child? */
+	bne	2f		/* return if parent */
 	li	r0,0
 	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
 	ld	r2,8(r29)
@@ -438,7 +440,7 @@ _GLOBAL(kernel_thread)
 	li	r0,__NR_exit	/* exit after child exits */
         li	r3,0
 	sc
-1:	addi	r1,r1,STACK_FRAME_OVERHEAD	
+2:	addi	r1,r1,STACK_FRAME_OVERHEAD
 	ld	r29,-24(r1)
 	ld	r30,-16(r1)
 	blr
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index e9be908f199..93ae5b169f4 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -78,7 +78,7 @@ struct of_device *of_device_alloc(struct device_node *np,
 	dev->dev.parent = parent;
 	dev->dev.release = of_release_dev;
 	dev->dev.archdata.of_node = np;
-	dev->dev.archdata.numa_node = of_node_to_nid(np);
+	set_dev_node(&dev->dev, of_node_to_nid(np));
 
 	if (bus_id)
 		strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index c9bf17eec31..48a347133f4 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -12,6 +12,7 @@
 
 #include <asm/lppaca.h>
 #include <asm/paca.h>
+#include <asm/sections.h>
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
@@ -79,6 +80,8 @@ void __init initialise_pacas(void)
 		new_paca->lock_token = 0x8000;
 		new_paca->paca_index = cpu;
 		new_paca->kernel_toc = kernel_toc;
+		new_paca->kernelbase = (unsigned long) _stext;
+		new_paca->kernel_msr = MSR_KERNEL;
 		new_paca->hw_cpu_id = 0xffff;
 		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
 		new_paca->__current = &init_task;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index ea0c61e09b7..01ce8c38bae 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -56,6 +56,34 @@ resource_size_t isa_mem_base;
 /* Default PCI flags is 0 */
 unsigned int ppc_pci_flags;
 
+static struct dma_mapping_ops *pci_dma_ops;
+
+void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
+{
+	pci_dma_ops = dma_ops;
+}
+
+struct dma_mapping_ops *get_pci_dma_ops(void)
+{
+	return pci_dma_ops;
+}
+EXPORT_SYMBOL(get_pci_dma_ops);
+
+int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	return dma_set_mask(&dev->dev, mask);
+}
+
+int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	int rc;
+
+	rc = dma_set_mask(&dev->dev, mask);
+	dev->dev.coherent_dma_mask = dev->dma_mask;
+
+	return rc;
+}
+
 struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 {
 	struct pci_controller *phb;
@@ -180,6 +208,26 @@ char __devinit *pcibios_setup(char *str)
 	return str;
 }
 
+void __devinit pcibios_setup_new_device(struct pci_dev *dev)
+{
+	struct dev_archdata *sd = &dev->dev.archdata;
+
+	sd->of_node = pci_device_to_OF_node(dev);
+
+	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
+	    sd->of_node ? sd->of_node->full_name : "<none>");
+
+	sd->dma_ops = pci_dma_ops;
+#ifdef CONFIG_PPC32
+	sd->dma_data = (void *)PCI_DRAM_OFFSET;
+#endif
+	set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+	if (ppc_md.pci_dma_dev_setup)
+		ppc_md.pci_dma_dev_setup(dev);
+}
+EXPORT_SYMBOL(pcibios_setup_new_device);
+
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -371,7 +419,7 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
 	struct pci_dev *pdev = NULL;
 	struct resource *found = NULL;
 	unsigned long prot = pgprot_val(protection);
-	unsigned long offset = pfn << PAGE_SHIFT;
+	resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT;
 	int i;
 
 	if (page_is_ram(pfn))
@@ -422,7 +470,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
-	resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT;
+	resource_size_t offset =
+		((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT;
 	struct resource *rp;
 	int ret;
 
@@ -731,11 +780,6 @@ static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev)
 
 	res->start = (res->start + offset) & mask;
 	res->end = (res->end + offset) & mask;
-
-	pr_debug("PCI:%s            %016llx-%016llx\n",
-		 pci_name(dev),
-		 (unsigned long long)res->start,
-		 (unsigned long long)res->end);
 }
 
 
@@ -781,6 +825,11 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev)
 			 (unsigned int)res->flags);
 
 		fixup_resource(res, dev);
+
+		pr_debug("PCI:%s            %016llx-%016llx\n",
+			 pci_name(dev),
+			 (unsigned long long)res->start,
+			 (unsigned long long)res->end);
 	}
 
 	/* Call machine specific resource fixup */
@@ -789,58 +838,127 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources);
 
-static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
+/* This function tries to figure out if a bridge resource has been initialized
+ * by the firmware or not. It doesn't have to be absolutely bullet proof, but
+ * things go more smoothly when it gets it right. It should covers cases such
+ * as Apple "closed" bridge resources and bare-metal pSeries unassigned bridges
+ */
+static int __devinit pcibios_uninitialized_bridge_resource(struct pci_bus *bus,
+							   struct resource *res)
 {
 	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pci_dev *dev = bus->self;
+	resource_size_t offset;
+	u16 command;
+	int i;
 
-	pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB");
+	/* We don't do anything if PCI_PROBE_ONLY is set */
+	if (ppc_pci_flags & PPC_PCI_PROBE_ONLY)
+		return 0;
 
-	/* Fixup PCI<->PCI bridges. Host bridges are handled separately, for
-	 * now differently between 32 and 64 bits.
-	 */
-	if (dev != NULL) {
-		struct resource *res;
-		int i;
+	/* Job is a bit different between memory and IO */
+	if (res->flags & IORESOURCE_MEM) {
+		/* If the BAR is non-0 (res != pci_mem_offset) then it's probably been
+		 * initialized by somebody
+		 */
+		if (res->start != hose->pci_mem_offset)
+			return 0;
 
-		for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
-			if ((res = bus->resource[i]) == NULL)
-				continue;
-			if (!res->flags)
-				continue;
-			if (i >= 3 && bus->self->transparent)
-				continue;
-			/* On PowerMac, Apple leaves bridge windows open over
-			 * an inaccessible region of memory space (0...fffff)
-			 * which is somewhat bogus, but that's what they think
-			 * means disabled...
-			 *
-			 * We clear those to force them to be reallocated later
-			 *
-			 * We detect such regions by the fact that the base is
-			 * equal to the pci_mem_offset of the host bridge and
-			 * their size is smaller than 1M.
-			 */
-			if (res->flags & IORESOURCE_MEM &&
-			    res->start == hose->pci_mem_offset &&
-			    res->end < 0x100000) {
-				printk(KERN_INFO
-				       "PCI: Closing bogus Apple Firmware"
-				       " region %d on bus 0x%02x\n",
-				       i, bus->number);
-				res->flags = 0;
-				continue;
-			}
+		/* The BAR is 0, let's check if memory decoding is enabled on
+		 * the bridge. If not, we consider it unassigned
+		 */
+		pci_read_config_word(dev, PCI_COMMAND, &command);
+		if ((command & PCI_COMMAND_MEMORY) == 0)
+			return 1;
 
-			pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n",
-				 pci_name(dev), i,
-				 (unsigned long long)res->start,\
-				 (unsigned long long)res->end,
-				 (unsigned int)res->flags);
+		/* Memory decoding is enabled and the BAR is 0. If any of the bridge
+		 * resources covers that starting address (0 then it's good enough for
+		 * us for memory
+		 */
+		for (i = 0; i < 3; i++) {
+			if ((hose->mem_resources[i].flags & IORESOURCE_MEM) &&
+			    hose->mem_resources[i].start == hose->pci_mem_offset)
+				return 0;
+		}
 
-			fixup_resource(res, dev);
+		/* Well, it starts at 0 and we know it will collide so we may as
+		 * well consider it as unassigned. That covers the Apple case.
+		 */
+		return 1;
+	} else {
+		/* If the BAR is non-0, then we consider it assigned */
+		offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+		if (((res->start - offset) & 0xfffffffful) != 0)
+			return 0;
+
+		/* Here, we are a bit different than memory as typically IO space
+		 * starting at low addresses -is- valid. What we do instead if that
+		 * we consider as unassigned anything that doesn't have IO enabled
+		 * in the PCI command register, and that's it.
+		 */
+		pci_read_config_word(dev, PCI_COMMAND, &command);
+		if (command & PCI_COMMAND_IO)
+			return 0;
+
+		/* It's starting at 0 and IO is disabled in the bridge, consider
+		 * it unassigned
+		 */
+		return 1;
+	}
+}
+
+/* Fixup resources of a PCI<->PCI bridge */
+static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
+{
+	struct resource *res;
+	int i;
+
+	struct pci_dev *dev = bus->self;
+
+	for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
+		if ((res = bus->resource[i]) == NULL)
+			continue;
+		if (!res->flags)
+			continue;
+		if (i >= 3 && bus->self->transparent)
+			continue;
+
+		pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n",
+			 pci_name(dev), i,
+			 (unsigned long long)res->start,\
+			 (unsigned long long)res->end,
+			 (unsigned int)res->flags);
+
+		/* Perform fixup */
+		fixup_resource(res, dev);
+
+		/* Try to detect uninitialized P2P bridge resources,
+		 * and clear them out so they get re-assigned later
+		 */
+		if (pcibios_uninitialized_bridge_resource(bus, res)) {
+			res->flags = 0;
+			pr_debug("PCI:%s            (unassigned)\n", pci_name(dev));
+		} else {
+
+			pr_debug("PCI:%s            %016llx-%016llx\n",
+				 pci_name(dev),
+				 (unsigned long long)res->start,
+				 (unsigned long long)res->end);
 		}
 	}
+}
+
+static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
+{
+	struct pci_dev *dev = bus->self;
+
+	pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB");
+
+	/* Fixup PCI<->PCI bridges. Host bridges are handled separately, for
+	 * now differently between 32 and 64 bits.
+	 */
+	if (dev != NULL)
+		pcibios_fixup_bridge(bus);
 
 	/* Additional setup that is different between 32 and 64 bits for now */
 	pcibios_do_bus_setup(bus);
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 88db4ffaf11..131b1dfa68c 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -53,12 +53,19 @@ LIST_HEAD(hose_list);
 
 static int pci_bus_count;
 
+/* This will remain NULL for now, until isa-bridge.c is made common
+ * to both 32-bit and 64-bit.
+ */
+struct pci_dev *isa_bridge_pcidev;
+EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
+
 static void
-fixup_hide_host_resource_fsl(struct pci_dev* dev)
+fixup_hide_host_resource_fsl(struct pci_dev *dev)
 {
 	int i, class = dev->class >> 8;
 
-	if ((class == PCI_CLASS_PROCESSOR_POWERPC) &&
+	if ((class == PCI_CLASS_PROCESSOR_POWERPC ||
+	     class == PCI_CLASS_BRIDGE_OTHER) &&
 		(dev->hdr_type == PCI_HEADER_TYPE_NORMAL) &&
 		(dev->bus->parent == NULL)) {
 		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
@@ -424,6 +431,7 @@ void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 	unsigned long io_offset;
 	struct resource *res;
 	int i;
+	struct pci_dev *dev;
 
 	/* Hookup PHB resources */
 	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
@@ -457,6 +465,12 @@ void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 			bus->resource[i+1] = res;
 		}
 	}
+
+	if (ppc_md.pci_dma_bus_setup)
+		ppc_md.pci_dma_bus_setup(bus);
+
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		pcibios_setup_new_device(dev);
 }
 
 /* the next one is stolen from the alpha port... */
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 30eedfc5a56..8247cff1cb3 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -52,35 +52,6 @@ EXPORT_SYMBOL(pci_io_base);
 
 LIST_HEAD(hose_list);
 
-static struct dma_mapping_ops *pci_dma_ops;
-
-void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
-{
-	pci_dma_ops = dma_ops;
-}
-
-struct dma_mapping_ops *get_pci_dma_ops(void)
-{
-	return pci_dma_ops;
-}
-EXPORT_SYMBOL(get_pci_dma_ops);
-
-
-int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
-{
-	return dma_set_mask(&dev->dev, mask);
-}
-
-int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
-{
-	int rc;
-
-	rc = dma_set_mask(&dev->dev, mask);
-	dev->dev.coherent_dma_mask = dev->dma_mask;
-
-	return rc;
-}
-
 static void fixup_broken_pcnet32(struct pci_dev* dev)
 {
 	if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
@@ -548,26 +519,6 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-void __devinit pcibios_setup_new_device(struct pci_dev *dev)
-{
-	struct dev_archdata *sd = &dev->dev.archdata;
-
-	sd->of_node = pci_device_to_OF_node(dev);
-
-	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
-	    sd->of_node ? sd->of_node->full_name : "<none>");
-
-	sd->dma_ops = pci_dma_ops;
-#ifdef CONFIG_NUMA
-	sd->numa_node = pcibus_to_node(dev->bus);
-#else
-	sd->numa_node = -1;
-#endif
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
-}
-EXPORT_SYMBOL(pcibios_setup_new_device);
-
 void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index e1ea4fe5cfb..8edc2359c41 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -119,6 +119,9 @@ EXPORT_SYMBOL(flush_instruction_cache);
 EXPORT_SYMBOL(flush_tlb_kernel_range);
 EXPORT_SYMBOL(flush_tlb_page);
 EXPORT_SYMBOL(_tlbie);
+#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
+EXPORT_SYMBOL(_tlbil_va);
+#endif
 #endif
 EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 87d83c56b31..3a2dc7e6586 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -888,9 +888,10 @@ static u64 __init dt_mem_next_cell(int s, cell_t **cellp)
  */
 static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 {
-	cell_t *dm, *ls;
+	cell_t *dm, *ls, *usm;
 	unsigned long l, n, flags;
 	u64 base, size, lmb_size;
+	unsigned int is_kexec_kdump = 0, rngs;
 
 	ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
 	if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t))
@@ -905,6 +906,12 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(cell_t))
 		return 0;
 
+	/* check if this is a kexec/kdump kernel. */
+	usm = (cell_t *)of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
+						 &l);
+	if (usm != NULL)
+		is_kexec_kdump = 1;
+
 	for (; n != 0; --n) {
 		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
 		flags = dm[3];
@@ -915,13 +922,34 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 		if ((flags & 0x80) || !(flags & 0x8))
 			continue;
 		size = lmb_size;
-		if (iommu_is_off) {
-			if (base >= 0x80000000ul)
+		rngs = 1;
+		if (is_kexec_kdump) {
+			/*
+			 * For each lmb in ibm,dynamic-memory, a corresponding
+			 * entry in linux,drconf-usable-memory property contains
+			 * a counter 'p' followed by 'p' (base, size) duple.
+			 * Now read the counter from
+			 * linux,drconf-usable-memory property
+			 */
+			rngs = dt_mem_next_cell(dt_root_size_cells, &usm);
+			if (!rngs) /* there are no (base, size) duple */
 				continue;
-			if ((base + size) > 0x80000000ul)
-				size = 0x80000000ul - base;
 		}
-		lmb_add(base, size);
+		do {
+			if (is_kexec_kdump) {
+				base = dt_mem_next_cell(dt_root_addr_cells,
+							 &usm);
+				size = dt_mem_next_cell(dt_root_size_cells,
+							 &usm);
+			}
+			if (iommu_is_off) {
+				if (base >= 0x80000000ul)
+					continue;
+				if ((base + size) > 0x80000000ul)
+					size = 0x80000000ul - base;
+			}
+			lmb_add(base, size);
+		} while (--rngs);
 	}
 	lmb_dump_all();
 	return 0;
@@ -1164,6 +1192,9 @@ void __init early_init_devtree(void *params)
 
 	/* Reserve LMB regions used by kernel, initrd, dt, etc... */
 	lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
+	/* If relocatable, reserve first 32k for interrupt vectors etc. */
+	if (PHYSICAL_START > MEMORY_START)
+		lmb_reserve(MEMORY_START, 0x8000);
 	reserve_kdump_trampoline();
 	reserve_crashkernel();
 	early_reserve_mem();
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index b72849ac7db..2fdbc18ae94 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -732,7 +732,7 @@ static struct fake_elf {
 			u32	ignore_me;
 		} rpadesc;
 	} rpanote;
-} fake_elf = {
+} fake_elf __section(.fakeelf) = {
 	.elfhdr = {
 		.e_ident = { 0x7f, 'E', 'L', 'F',
 			     ELFCLASS32, ELFDATA2MSB, EV_CURRENT },
@@ -774,13 +774,13 @@ static struct fake_elf {
 		.type = 0x12759999,
 		.name = "IBM,RPA-Client-Config",
 		.rpadesc = {
-			.lpar_affinity = 0,
-			.min_rmo_size = 64,	/* in megabytes */
+			.lpar_affinity = 1,
+			.min_rmo_size = 128,	/* in megabytes */
 			.min_rmo_percent = 0,
-			.max_pft_size = 48,	/* 2^48 bytes max PFT size */
+			.max_pft_size = 46,	/* 2^46 bytes max PFT size */
 			.splpar = 1,
 			.min_load = ~0U,
-			.new_mem_def = 0
+			.new_mem_def = 1
 		}
 	}
 };
@@ -1321,7 +1321,7 @@ static void __init prom_initialize_tce_table(void)
  *
  * -- Cort
  */
-extern void __secondary_hold(void);
+extern char __secondary_hold;
 extern unsigned long __secondary_hold_spinloop;
 extern unsigned long __secondary_hold_acknowledge;
 
@@ -1342,13 +1342,7 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_spinloop);
 	unsigned long *acknowledge
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
-#ifdef CONFIG_PPC64
-	/* __secondary_hold is actually a descriptor, not the text address */
-	unsigned long secondary_hold
-		= __pa(*PTRRELOC((unsigned long *)__secondary_hold));
-#else
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
-#endif
 
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
@@ -2315,13 +2309,14 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 
 unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 			       unsigned long pp,
-			       unsigned long r6, unsigned long r7)
+			       unsigned long r6, unsigned long r7,
+			       unsigned long kbase)
 {	
 	struct prom_t *_prom;
 	unsigned long hdr;
-	unsigned long offset = reloc_offset();
 
 #ifdef CONFIG_PPC32
+	unsigned long offset = reloc_offset();
 	reloc_got2(offset);
 #endif
 
@@ -2355,9 +2350,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	RELOC(of_platform) = prom_find_machine_type();
 
+#ifndef CONFIG_RELOCATABLE
 	/* Bail if this is a kdump kernel. */
 	if (PHYSICAL_START > 0)
 		prom_panic("Error: You can't boot a kdump kernel from OF!\n");
+#endif
 
 	/*
 	 * Check for an initrd
@@ -2377,7 +2374,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Copy the CPU hold code
 	 */
 	if (RELOC(of_platform) != PLATFORM_POWERMAC)
-		copy_and_flush(0, KERNELBASE + offset, 0x100, 0);
+		copy_and_flush(0, kbase, 0x100, 0);
 
 	/*
 	 * Do early parsing of command line
@@ -2480,7 +2477,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	reloc_got2(-offset);
 #endif
 
-	__start(hdr, KERNELBASE + offset, 0);
+	__start(hdr, kbase, 0);
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
new file mode 100644
index 00000000000..b47a0e1ab00
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -0,0 +1,87 @@
+/*
+ * Code to process dynamic relocations in the kernel.
+ *
+ * Copyright 2008 Paul Mackerras, 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 <asm/ppc_asm.h>
+
+RELA = 7
+RELACOUNT = 0x6ffffff9
+R_PPC64_RELATIVE = 22
+
+/*
+ * r3 = desired final address of kernel
+ */
+_GLOBAL(relocate)
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r12		/* r12 has runtime addr of label 0 */
+	mtlr	r0
+	ld	r11,(p_dyn - 0b)(r12)
+	add	r11,r11,r12	/* r11 has runtime addr of .dynamic section */
+	ld	r9,(p_rela - 0b)(r12)
+	add	r9,r9,r12	/* r9 has runtime addr of .rela.dyn section */
+	ld	r10,(p_st - 0b)(r12)
+	add	r10,r10,r12	/* r10 has runtime addr of _stext */
+
+	/*
+	 * Scan the dynamic section for the RELA and RELACOUNT entries.
+	 */
+	li	r7,0
+	li	r8,0
+1:	ld	r6,0(r11)	/* get tag */
+	cmpdi	r6,0
+	beq	4f		/* end of list */
+	cmpdi	r6,RELA
+	bne	2f
+	ld	r7,8(r11)	/* get RELA pointer in r7 */
+	b	3f
+2:	addis	r6,r6,(-RELACOUNT)@ha
+	cmpdi	r6,RELACOUNT@l
+	bne	3f
+	ld	r8,8(r11)	/* get RELACOUNT value in r8 */
+3:	addi	r11,r11,16
+	b	1b
+4:	cmpdi	r7,0		/* check we have both RELA and RELACOUNT */
+	cmpdi	cr1,r8,0
+	beq	6f
+	beq	cr1,6f
+
+	/*
+	 * Work out linktime address of _stext and hence the
+	 * relocation offset to be applied.
+	 * cur_offset [r7] = rela.run [r9] - rela.link [r7]
+	 * _stext.link [r10] = _stext.run [r10] - cur_offset [r7]
+	 * final_offset [r3] = _stext.final [r3] - _stext.link [r10]
+	 */
+	subf	r7,r7,r9	/* cur_offset */
+	subf	r10,r7,r10
+	subf	r3,r10,r3	/* final_offset */
+
+	/*
+	 * Run through the list of relocations and process the
+	 * R_PPC64_RELATIVE ones.
+	 */
+	mtctr	r8
+5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
+	cmpwi	r0,R_PPC64_RELATIVE
+	bne	6f
+	ld	r6,0(r9)	/* reloc->r_offset */
+	ld	r0,16(r9)	/* reloc->r_addend */
+	add	r0,r0,r3
+	stdx	r0,r7,r6
+	addi	r9,r9,24
+	bdnz	5b
+
+6:	blr
+
+p_dyn:	.llong	__dynamic_start - 0b
+p_rela:	.llong	__rela_dyn_start - 0b
+p_st:	.llong	_stext - 0b
+
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9cc5a52711e..5ec56ff03e8 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -254,8 +254,21 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	/* If we are a Freescale core do a simple check so
 	 * we dont have to keep adding cases in the future */
 	if (PVR_VER(pvr) & 0x8000) {
-		maj = PVR_MAJ(pvr);
-		min = PVR_MIN(pvr);
+		switch (PVR_VER(pvr)) {
+		case 0x8000:	/* 7441/7450/7451, Voyager */
+		case 0x8001:	/* 7445/7455, Apollo 6 */
+		case 0x8002:	/* 7447/7457, Apollo 7 */
+		case 0x8003:	/* 7447A, Apollo 7 PM */
+		case 0x8004:	/* 7448, Apollo 8 */
+		case 0x800c:	/* 7410, Nitro */
+			maj = ((pvr >> 8) & 0xF);
+			min = PVR_MIN(pvr);
+			break;
+		default:	/* e500/book-e */
+			maj = PVR_MAJ(pvr);
+			min = PVR_MIN(pvr);
+			break;
+		}
 	} else {
 		switch (PVR_VER(pvr)) {
 			case 0x0020:	/* 403 family */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 066e65c59b5..c1a27626a94 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -111,7 +111,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  * This is called very early on the boot process, after a minimal
  * MMU environment has been set up but before MMU_init is called.
  */
-notrace void __init machine_init(unsigned long dt_ptr, unsigned long phys)
+notrace void __init machine_init(unsigned long dt_ptr)
 {
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
@@ -209,23 +209,12 @@ EXPORT_SYMBOL(nvram_sync);
 
 #endif /* CONFIG_NVRAM */
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
 int __init ppc_init(void)
 {
-	int cpu;
-
 	/* clear the progress line */
 	if (ppc_md.progress)
 		ppc_md.progress("             ", 0xffff);
 
-	/* register CPU devices */
-	for_each_possible_cpu(cpu) {
-		struct cpu *c = &per_cpu(cpu_devices, cpu);
-		c->hotpluggable = 1;
-		register_cpu(c, cpu);
-	}
-
 	/* call platform init */
 	if (ppc_md.init != NULL) {
 		ppc_md.init();
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 8b25f51f03b..843c0af210d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -255,9 +255,11 @@ void early_setup_secondary(void)
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
+extern unsigned long __secondary_hold_spinloop;
+extern void generic_secondary_smp_init(void);
+
 void smp_release_cpus(void)
 {
-	extern unsigned long __secondary_hold_spinloop;
 	unsigned long *ptr;
 
 	DBG(" -> smp_release_cpus()\n");
@@ -266,12 +268,11 @@ void smp_release_cpus(void)
 	 * all now so they can start to spin on their individual paca
 	 * spinloops. For non SMP kernels, the secondary cpus never get out
 	 * of the common spinloop.
-	 * This is useless but harmless on iSeries, secondaries are already
-	 * waiting on their paca spinloops. */
+	 */
 
 	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
 			- PHYSICAL_START);
-	*ptr = 1;
+	*ptr = __pa(generic_secondary_smp_init);
 	mb();
 
 	DBG(" <- smp_release_cpus()\n");
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index c27b10a1bd7..ff9f7010097 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -101,8 +101,7 @@ void smp_message_recv(int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
-		/* XXX Do we have to do this? */
-		set_need_resched();
+		/* we notice need_resched on exit */
 		break;
 	case PPC_MSG_CALL_FUNC_SINGLE:
 		generic_smp_call_function_single_interrupt();
diff --git a/arch/powerpc/kernel/softemu8xx.c b/arch/powerpc/kernel/softemu8xx.c
index c906c4bf683..23c8c5e7dc4 100644
--- a/arch/powerpc/kernel/softemu8xx.c
+++ b/arch/powerpc/kernel/softemu8xx.c
@@ -23,7 +23,6 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/user.h>
-#include <linux/a.out.h>
 #include <linux/interrupt.h>
 
 #include <asm/pgtable.h>
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
index e092c3cbdb9..86ac1d90d02 100644
--- a/arch/powerpc/kernel/swsusp_asm64.S
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -133,7 +133,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 
 	cmpdi	r12,0
 	beq-	nothing_to_copy
-	li	r15,512
+	li	r15,PAGE_SIZE>>3
 copyloop:
 	ld	r13,pbe_address(r12)
 	ld	r14,pbe_orig_address(r12)
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index d98634c7606..bb1cfcfdbbb 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -61,42 +61,6 @@ asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp,
 	return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x));
 }
 
-int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf)
-{
-	compat_ino_t ino;
-	long err;
-
-	if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) ||
-	    !new_valid_dev(stat->rdev))
-		return -EOVERFLOW;
-
-	ino = stat->ino;
-	if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
-		return -EOVERFLOW;
-
-	err  = access_ok(VERIFY_WRITE, statbuf, sizeof(*statbuf)) ? 0 : -EFAULT;
-	err |= __put_user(new_encode_dev(stat->dev), &statbuf->st_dev);
-	err |= __put_user(ino, &statbuf->st_ino);
-	err |= __put_user(stat->mode, &statbuf->st_mode);
-	err |= __put_user(stat->nlink, &statbuf->st_nlink);
-	err |= __put_user(stat->uid, &statbuf->st_uid);
-	err |= __put_user(stat->gid, &statbuf->st_gid);
-	err |= __put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev);
-	err |= __put_user(stat->size, &statbuf->st_size);
-	err |= __put_user(stat->atime.tv_sec, &statbuf->st_atime);
-	err |= __put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec);
-	err |= __put_user(stat->mtime.tv_sec, &statbuf->st_mtime);
-	err |= __put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec);
-	err |= __put_user(stat->ctime.tv_sec, &statbuf->st_ctime);
-	err |= __put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec);
-	err |= __put_user(stat->blksize, &statbuf->st_blksize);
-	err |= __put_user(stat->blocks, &statbuf->st_blocks);
-	err |= __put_user(0, &statbuf->__unused4[0]);
-	err |= __put_user(0, &statbuf->__unused4[1]);
-
-	return err;
-}
-
 /* Note: it is necessary to treat option as an unsigned int,
  * with the corresponding cast to a signed int to insure that the 
  * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode)
@@ -107,77 +71,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2)
 	return sys_sysfs((int)option, arg1, arg2);
 }
 
-asmlinkage long compat_sys_pause(void)
-{
-	current->state = TASK_INTERRUPTIBLE;
-	schedule();
-	
-	return -ERESTARTNOHAND;
-}
-
-static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i)
-{
-	long usec;
-
-	if (!access_ok(VERIFY_READ, i, sizeof(*i)))
-		return -EFAULT;
-	if (__get_user(o->tv_sec, &i->tv_sec))
-		return -EFAULT;
-	if (__get_user(usec, &i->tv_usec))
-		return -EFAULT;
-	o->tv_nsec = usec * 1000;
-	return 0;
-}
-
-static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i)
-{
-	return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) ||
-		(__put_user(i->tv_sec, &o->tv_sec) |
-		 __put_user(i->tv_usec, &o->tv_usec)));
-}
-
-
-
-
-/* Translations due to time_t size differences.  Which affects all
-   sorts of things, like timeval and itimerval.  */
-extern struct timezone sys_tz;
-
-asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
-{
-	if (tv) {
-		struct timeval ktv;
-		do_gettimeofday(&ktv);
-		if (put_tv32(tv, &ktv))
-			return -EFAULT;
-	}
-	if (tz) {
-		if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
-			return -EFAULT;
-	}
-	
-	return 0;
-}
-
-
-
-asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
-{
-	struct timespec kts;
-	struct timezone ktz;
-	
- 	if (tv) {
-		if (get_ts32(&kts, tv))
-			return -EFAULT;
-	}
-	if (tz) {
-		if (copy_from_user(&ktz, tz, sizeof(ktz)))
-			return -EFAULT;
-	}
-
-	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
-}
-
 #ifdef CONFIG_SYSVIPC
 long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr,
 	       u32 fifth)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 56d172d16e5..86a2ffccef2 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -15,18 +15,24 @@
 #include <asm/firmware.h>
 #include <asm/hvcall.h>
 #include <asm/prom.h>
-#include <asm/paca.h>
-#include <asm/lppaca.h>
 #include <asm/machdep.h>
 #include <asm/smp.h>
 
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#include <asm/lppaca.h>
+#endif
+
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static DEFINE_PER_CPU(struct kobject *, cache_toplevel);
 
-/* SMT stuff */
+/*
+ * SMT snooze delay stuff, 64-bit only for now
+ */
+
+#ifdef CONFIG_PPC64
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 /* Time in microseconds we delay before sleeping in the idle loop */
 DEFINE_PER_CPU(unsigned long, smt_snooze_delay) = { 100 };
 
@@ -106,7 +112,7 @@ static int __init setup_smt_snooze_delay(char *str)
 }
 __setup("smt-snooze-delay=", setup_smt_snooze_delay);
 
-#endif /* CONFIG_PPC_MULTIPLATFORM */
+#endif /* CONFIG_PPC64 */
 
 /*
  * Enabling PMCs will slow partition context switch times so we only do
@@ -115,7 +121,7 @@ __setup("smt-snooze-delay=", setup_smt_snooze_delay);
 
 static DEFINE_PER_CPU(char, pmcs_enabled);
 
-void ppc64_enable_pmcs(void)
+void ppc_enable_pmcs(void)
 {
 	/* Only need to enable them once */
 	if (__get_cpu_var(pmcs_enabled))
@@ -126,8 +132,9 @@ void ppc64_enable_pmcs(void)
 	if (ppc_md.enable_pmcs)
 		ppc_md.enable_pmcs();
 }
-EXPORT_SYMBOL(ppc64_enable_pmcs);
+EXPORT_SYMBOL(ppc_enable_pmcs);
 
+#if defined(CONFIG_6xx) || defined(CONFIG_PPC64)
 /* XXX convert to rusty's on_one_cpu */
 static unsigned long run_on_cpu(unsigned long cpu,
 			        unsigned long (*func)(unsigned long),
@@ -146,6 +153,7 @@ static unsigned long run_on_cpu(unsigned long cpu,
 
 	return ret;
 }
+#endif
 
 #define SYSFS_PMCSETUP(NAME, ADDRESS) \
 static unsigned long read_##NAME(unsigned long junk) \
@@ -154,7 +162,7 @@ static unsigned long read_##NAME(unsigned long junk) \
 } \
 static unsigned long write_##NAME(unsigned long val) \
 { \
-	ppc64_enable_pmcs(); \
+	ppc_enable_pmcs(); \
 	mtspr(ADDRESS, val); \
 	return 0; \
 } \
@@ -184,28 +192,53 @@ static ssize_t __used \
  * that are implemented on the current processor
  */
 
+#if defined(CONFIG_PPC64)
+#define HAS_PPC_PMC_CLASSIC	1
+#define HAS_PPC_PMC_IBM		1
+#define HAS_PPC_PMC_PA6T	1
+#elif defined(CONFIG_6xx)
+#define HAS_PPC_PMC_CLASSIC	1
+#define HAS_PPC_PMC_IBM		1
+#define HAS_PPC_PMC_G4		1
+#endif
+
+
+#ifdef HAS_PPC_PMC_CLASSIC
 SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
 SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
-SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
 SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
 SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
 SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
 SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
 SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
 SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
+
+#ifdef HAS_PPC_PMC_G4
+SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
+#endif
+
+#ifdef CONFIG_PPC64
 SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
 SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+
+SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
 SYSFS_PMCSETUP(purr, SPRN_PURR);
 SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
 
+static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL);
+static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr);
+static SYSDEV_ATTR(purr, 0600, show_purr, store_purr);
+#endif /* CONFIG_PPC64 */
+
+#ifdef HAS_PPC_PMC_PA6T
 SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0);
 SYSFS_PMCSETUP(pa6t_pmc1, SPRN_PA6T_PMC1);
 SYSFS_PMCSETUP(pa6t_pmc2, SPRN_PA6T_PMC2);
 SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
 SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
 SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);
-
 #ifdef CONFIG_DEBUG_KERNEL
 SYSFS_PMCSETUP(hid0, SPRN_HID0);
 SYSFS_PMCSETUP(hid1, SPRN_HID1);
@@ -236,28 +269,37 @@ SYSFS_PMCSETUP(tsr1, SPRN_PA6T_TSR1);
 SYSFS_PMCSETUP(tsr2, SPRN_PA6T_TSR2);
 SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3);
 #endif /* CONFIG_DEBUG_KERNEL */
+#endif /* HAS_PPC_PMC_PA6T */
 
-static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
-static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL);
-static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr);
-static SYSDEV_ATTR(purr, 0600, show_purr, store_purr);
-
+#ifdef HAS_PPC_PMC_IBM
 static struct sysdev_attribute ibm_common_attrs[] = {
 	_SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
 	_SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
 };
+#endif /* HAS_PPC_PMC_G4 */
+
+#ifdef HAS_PPC_PMC_G4
+static struct sysdev_attribute g4_common_attrs[] = {
+	_SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
+	_SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
+	_SYSDEV_ATTR(mmcr2, 0600, show_mmcr2, store_mmcr2),
+};
+#endif /* HAS_PPC_PMC_G4 */
 
-static struct sysdev_attribute ibm_pmc_attrs[] = {
+static struct sysdev_attribute classic_pmc_attrs[] = {
 	_SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1),
 	_SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2),
 	_SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3),
 	_SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4),
 	_SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5),
 	_SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6),
+#ifdef CONFIG_PPC64
 	_SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7),
 	_SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8),
+#endif
 };
 
+#ifdef HAS_PPC_PMC_PA6T
 static struct sysdev_attribute pa6t_attrs[] = {
 	_SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
 	_SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
@@ -298,6 +340,8 @@ static struct sysdev_attribute pa6t_attrs[] = {
 	_SYSDEV_ATTR(tsr3, 0600, show_tsr3, store_tsr3),
 #endif /* CONFIG_DEBUG_KERNEL */
 };
+#endif /* HAS_PPC_PMC_PA6T */
+#endif /* HAS_PPC_PMC_CLASSIC */
 
 struct cache_desc {
 	struct kobject kobj;
@@ -588,23 +632,36 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 	struct sysdev_attribute *attrs, *pmc_attrs;
 	int i, nattrs;
 
+#ifdef CONFIG_PPC64
 	if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
 			cpu_has_feature(CPU_FTR_SMT))
 		sysdev_create_file(s, &attr_smt_snooze_delay);
+#endif
 
 	/* PMC stuff */
 	switch (cur_cpu_spec->pmc_type) {
+#ifdef HAS_PPC_PMC_IBM
 	case PPC_PMC_IBM:
 		attrs = ibm_common_attrs;
 		nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute);
-		pmc_attrs = ibm_pmc_attrs;
+		pmc_attrs = classic_pmc_attrs;
 		break;
+#endif /* HAS_PPC_PMC_IBM */
+#ifdef HAS_PPC_PMC_G4
+	case PPC_PMC_G4:
+		attrs = g4_common_attrs;
+		nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute);
+		pmc_attrs = classic_pmc_attrs;
+		break;
+#endif /* HAS_PPC_PMC_G4 */
+#ifdef HAS_PPC_PMC_PA6T
 	case PPC_PMC_PA6T:
 		/* PA Semi starts counting at PMC0 */
 		attrs = pa6t_attrs;
 		nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute);
 		pmc_attrs = NULL;
 		break;
+#endif /* HAS_PPC_PMC_PA6T */
 	default:
 		attrs = NULL;
 		nattrs = 0;
@@ -618,6 +675,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 		for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
 			sysdev_create_file(s, &pmc_attrs[i]);
 
+#ifdef CONFIG_PPC64
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		sysdev_create_file(s, &attr_mmcra);
 
@@ -629,6 +687,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_DSCR))
 		sysdev_create_file(s, &attr_dscr);
+#endif /* CONFIG_PPC64 */
 
 	create_cache_info(s);
 }
@@ -641,16 +700,9 @@ static void remove_cache_info(struct sys_device *sysdev)
 	int cpu = sysdev->id;
 
 	cache_desc = per_cpu(cache_desc, cpu);
-	if (cache_desc != NULL) {
-		sysfs_remove_file(&cache_desc->kobj, &cache_size_attr.attr);
-		sysfs_remove_file(&cache_desc->kobj, &cache_line_size_attr.attr);
-		sysfs_remove_file(&cache_desc->kobj, &cache_type_attr.attr);
-		sysfs_remove_file(&cache_desc->kobj, &cache_level_attr.attr);
-		sysfs_remove_file(&cache_desc->kobj, &cache_nr_sets_attr.attr);
-		sysfs_remove_file(&cache_desc->kobj, &cache_assoc_attr.attr);
-
+	if (cache_desc != NULL)
 		kobject_put(&cache_desc->kobj);
-	}
+
 	cache_toplevel = per_cpu(cache_toplevel, cpu);
 	if (cache_toplevel != NULL)
 		kobject_put(cache_toplevel);
@@ -671,17 +723,28 @@ static void unregister_cpu_online(unsigned int cpu)
 
 	/* PMC stuff */
 	switch (cur_cpu_spec->pmc_type) {
+#ifdef HAS_PPC_PMC_IBM
 	case PPC_PMC_IBM:
 		attrs = ibm_common_attrs;
 		nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute);
-		pmc_attrs = ibm_pmc_attrs;
+		pmc_attrs = classic_pmc_attrs;
+		break;
+#endif /* HAS_PPC_PMC_IBM */
+#ifdef HAS_PPC_PMC_G4
+	case PPC_PMC_G4:
+		attrs = g4_common_attrs;
+		nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute);
+		pmc_attrs = classic_pmc_attrs;
 		break;
+#endif /* HAS_PPC_PMC_G4 */
+#ifdef HAS_PPC_PMC_PA6T
 	case PPC_PMC_PA6T:
 		/* PA Semi starts counting at PMC0 */
 		attrs = pa6t_attrs;
 		nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute);
 		pmc_attrs = NULL;
 		break;
+#endif /* HAS_PPC_PMC_PA6T */
 	default:
 		attrs = NULL;
 		nattrs = 0;
@@ -695,6 +758,7 @@ static void unregister_cpu_online(unsigned int cpu)
 		for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
 			sysdev_remove_file(s, &pmc_attrs[i]);
 
+#ifdef CONFIG_PPC64
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		sysdev_remove_file(s, &attr_mmcra);
 
@@ -706,6 +770,7 @@ static void unregister_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_DSCR))
 		sysdev_remove_file(s, &attr_dscr);
+#endif /* CONFIG_PPC64 */
 
 	remove_cache_info(s);
 }
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 81ccb8dd1a5..f5def6cf5cd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -23,7 +23,6 @@
 #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>
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 2750fbab197..434c92a85c0 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1232,7 +1232,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	else
 		viodev->dev.archdata.dma_ops = &dma_iommu_ops;
 	viodev->dev.archdata.dma_data = vio_build_iommu_table(viodev);
-	viodev->dev.archdata.numa_node = of_node_to_nid(of_node);
+	set_dev_node(&viodev->dev, of_node_to_nid(of_node));
 
 	/* init generic 'struct device' fields: */
 	viodev->dev.parent = &vio_bus_device.dev;
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 9f6c1ca1739..b39c27ed791 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -187,6 +187,24 @@ SECTIONS
 		*(.machine.desc)
 		__machine_desc_end = . ;
 	}
+	. = ALIGN(8);
+	.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) }
+	.dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
+	.dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
+	{
+		__dynamic_start = .;
+		*(.dynamic)
+	}
+	.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
+	.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
+	.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
+	{
+		__rela_dyn_start = .;
+		*(.rela*)
+	}
+
+	/* Fake ELF header containing RPA note; for addnote */
+	.fakeelf : AT(ADDR(.fakeelf) - LOAD_OFFSET) { *(.fakeelf) }
 
 	/* freed after init ends here */
 	. = ALIGN(PAGE_SIZE);