Merge branch 'linus' into perfcounters/core

Conflicts:
	arch/x86/include/asm/kmap_types.h
	include/linux/mm.h

	include/asm-generic/kmap_types.h

Merge reason: We crossed changes with kmap_types.h cleanups in mainline.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

30 files changed, 1745 insertions, 1469 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a2c6834..612b0c4 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   firmware.o nvram_64.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
-obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
+obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
@@ -82,6 +82,7 @@ obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 pci64-$(CONFIG_PPC64)		+= pci_dn.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
@@ -111,6 +112,7 @@ obj-y				+= ppc_save_regs.o
 endif
 
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
+extra-$(CONFIG_ALTIVEC)		+= vector.o
 extra-$(CONFIG_PPC64)		+= entry_64.o
 
 extra-y				+= systbl_chk.i
@@ -123,6 +125,7 @@ PHONY += systbl_chk
 systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i
 	$(call cmd,systbl_chk)
 
+ifeq ($(CONFIG_PPC_OF_BOOT_TRAMPOLINE),y)
 $(obj)/built-in.o:		prom_init_check
 
 quiet_cmd_prom_init_check = CALL    $<
@@ -131,5 +134,6 @@ quiet_cmd_prom_init_check = CALL    $<
 PHONY += prom_init_check
 prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o
 	$(call cmd,prom_init_check)
+endif
 
 clean-files := vmlinux.lds
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 5ffcfaa..a5b632e5 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -24,6 +24,7 @@
 #include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/cputable.h>
+#include <asm/emulated_ops.h>
 
 struct aligninfo {
 	unsigned char len;
@@ -730,8 +731,10 @@ int fix_alignment(struct pt_regs *regs)
 	areg = dsisr & 0x1f;		/* register to update */
 
 #ifdef CONFIG_SPE
-	if ((instr >> 26) == 0x4)
+	if ((instr >> 26) == 0x4) {
+		PPC_WARN_EMULATED(spe);
 		return emulate_spe(regs, reg, instr);
+	}
 #endif
 
 	instr = (dsisr >> 10) & 0x7f;
@@ -783,23 +786,28 @@ int fix_alignment(struct pt_regs *regs)
 			flags |= SPLT;
 			nb = 8;
 		}
+		PPC_WARN_EMULATED(vsx);
 		return emulate_vsx(addr, reg, areg, regs, flags, nb);
 	}
 #endif
 	/* A size of 0 indicates an instruction we don't support, with
 	 * the exception of DCBZ which is handled as a special case here
 	 */
-	if (instr == DCBZ)
+	if (instr == DCBZ) {
+		PPC_WARN_EMULATED(dcbz);
 		return emulate_dcbz(regs, addr);
+	}
 	if (unlikely(nb == 0))
 		return 0;
 
 	/* Load/Store Multiple instructions are handled in their own
 	 * function
 	 */
-	if (flags & M)
+	if (flags & M) {
+		PPC_WARN_EMULATED(multiple);
 		return emulate_multiple(regs, addr, reg, nb,
 					flags, instr, swiz);
+	}
 
 	/* Verify the address of the operand */
 	if (unlikely(user_mode(regs) &&
@@ -816,8 +824,12 @@ int fix_alignment(struct pt_regs *regs)
 	}
 
 	/* Special case for 16-byte FP loads and stores */
-	if (nb == 16)
+	if (nb == 16) {
+		PPC_WARN_EMULATED(fp_pair);
 		return emulate_fp_pair(addr, reg, flags);
+	}
+
+	PPC_WARN_EMULATED(unaligned);
 
 	/* If we are loading, get the data from user space, else
 	 * get it from register values
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index e981d1c..561b646 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -122,8 +122,6 @@ int main(void)
 	DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
 	DEFINE(PACACURRENT, offsetof(struct paca_struct, __current));
 	DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr));
-	DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
-	DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
 	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
 	DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
 	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
@@ -132,35 +130,30 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
 	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
-	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
-	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
-	DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
 					    context.low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
 					    context.high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
+#endif /* CONFIG_PPC_MM_SLICES */
+#ifdef CONFIG_PPC_STD_MMU_64
+	DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
+	DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
+	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
+	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
+	DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
+#ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
 	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
-
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
 	DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb));
-	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
-	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
-	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
-	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
-	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
-	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr));
-	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
-	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
-
 	DEFINE(SLBSHADOW_STACKVSID,
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid));
 	DEFINE(SLBSHADOW_STACKESID,
@@ -170,6 +163,15 @@ int main(void)
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
 	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
+#endif /* CONFIG_PPC_STD_MMU_64 */
+	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
+	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
+	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
+	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
+	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
+	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
+	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3e33fb9..4a24a2f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -427,7 +427,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (architected)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE |
+			MMU_FTR_TLBIE_206,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
@@ -441,7 +442,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE |
+			MMU_FTR_TLBIE_206,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
new file mode 100644
index 0000000..68ccf11
--- /dev/null
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -0,0 +1,163 @@
+/*
+ * Contains routines needed to support swiotlb for ppc.
+ *
+ * Copyright (C) 2009 Becky Bruce, Freescale Semiconductor
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/pfn.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pci.h>
+
+#include <asm/machdep.h>
+#include <asm/swiotlb.h>
+#include <asm/dma.h>
+#include <asm/abs_addr.h>
+
+int swiotlb __read_mostly;
+unsigned int ppc_swiotlb_enable;
+
+void *swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t addr)
+{
+	unsigned long pfn = PFN_DOWN(swiotlb_bus_to_phys(hwdev, addr));
+	void *pageaddr = page_address(pfn_to_page(pfn));
+
+	if (pageaddr != NULL)
+		return pageaddr + (addr % PAGE_SIZE);
+	return NULL;
+}
+
+dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
+{
+	return paddr + get_dma_direct_offset(hwdev);
+}
+
+phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
+
+{
+	return baddr - get_dma_direct_offset(hwdev);
+}
+
+/*
+ * Determine if an address needs bounce buffering via swiotlb.
+ * Going forward I expect the swiotlb code to generalize on using
+ * a dma_ops->addr_needs_map, and this function will move from here to the
+ * generic swiotlb code.
+ */
+int
+swiotlb_arch_address_needs_mapping(struct device *hwdev, dma_addr_t addr,
+				   size_t size)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(hwdev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->addr_needs_map(hwdev, addr, size);
+}
+
+/*
+ * Determine if an address is reachable by a pci device, or if we must bounce.
+ */
+static int
+swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
+{
+	u64 mask = dma_get_mask(hwdev);
+	dma_addr_t max;
+	struct pci_controller *hose;
+	struct pci_dev *pdev = to_pci_dev(hwdev);
+
+	hose = pci_bus_to_host(pdev->bus);
+	max = hose->dma_window_base_cur + hose->dma_window_size;
+
+	/* check that we're within mapped pci window space */
+	if ((addr + size > max) | (addr < hose->dma_window_base_cur))
+		return 1;
+
+	return !is_buffer_dma_capable(mask, addr, size);
+}
+
+static int
+swiotlb_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
+{
+	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+}
+
+
+/*
+ * At the moment, all platforms that use this code only require
+ * swiotlb to be used if we're operating on HIGHMEM.  Since
+ * we don't ever call anything other than map_sg, unmap_sg,
+ * map_page, and unmap_page on highmem, use normal dma_ops
+ * for everything else.
+ */
+struct dma_mapping_ops swiotlb_dma_ops = {
+	.alloc_coherent = dma_direct_alloc_coherent,
+	.free_coherent = dma_direct_free_coherent,
+	.map_sg = swiotlb_map_sg_attrs,
+	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.dma_supported = swiotlb_dma_supported,
+	.map_page = swiotlb_map_page,
+	.unmap_page = swiotlb_unmap_page,
+	.addr_needs_map = swiotlb_addr_needs_map,
+	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
+	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
+	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = swiotlb_sync_sg_for_device
+};
+
+struct dma_mapping_ops swiotlb_pci_dma_ops = {
+	.alloc_coherent = dma_direct_alloc_coherent,
+	.free_coherent = dma_direct_free_coherent,
+	.map_sg = swiotlb_map_sg_attrs,
+	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.dma_supported = swiotlb_dma_supported,
+	.map_page = swiotlb_map_page,
+	.unmap_page = swiotlb_unmap_page,
+	.addr_needs_map = swiotlb_pci_addr_needs_map,
+	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
+	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
+	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = swiotlb_sync_sg_for_device
+};
+
+static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	/* We are only intereted in device addition */
+	if (action != BUS_NOTIFY_ADD_DEVICE)
+		return 0;
+
+	/* May need to bounce if the device can't address all of DRAM */
+	if (dma_get_mask(dev) < lmb_end_of_DRAM())
+		set_dma_ops(dev, &swiotlb_dma_ops);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_swiotlb_plat_bus_notifier = {
+	.notifier_call = ppc_swiotlb_bus_notify,
+	.priority = 0,
+};
+
+static struct notifier_block ppc_swiotlb_of_bus_notifier = {
+	.notifier_call = ppc_swiotlb_bus_notify,
+	.priority = 0,
+};
+
+int __init swiotlb_setup_bus_notifier(void)
+{
+	bus_register_notifier(&platform_bus_type,
+			      &ppc_swiotlb_plat_bus_notifier);
+	bus_register_notifier(&of_platform_bus_type,
+			      &ppc_swiotlb_of_bus_notifier);
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 6b02793..20a60d6 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -19,7 +19,7 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
-static unsigned long get_dma_direct_offset(struct device *dev)
+unsigned long get_dma_direct_offset(struct device *dev)
 {
 	if (dev)
 		return (unsigned long)dev->archdata.dma_data;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
new file mode 100644
index 0000000..eb89811
--- /dev/null
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -0,0 +1,978 @@
+/*
+ * This file contains the 64-bit "server" PowerPC variant
+ * of the low level exception handling including exception
+ * vectors, exception return, part of the slb and stab
+ * handling and other fixed offset specific things.
+ *
+ * This file is meant to be #included from head_64.S due to
+ * position dependant assembly.
+ *
+ * Most of this originates from head_64.S and thus has the same
+ * copyright history.
+ *
+ */
+
+/*
+ * We layout physical memory as follows:
+ * 0x0000 - 0x00ff : Secondary processor spin code
+ * 0x0100 - 0x2fff : pSeries Interrupt prologs
+ * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
+ * 0x6000 - 0x6fff : Initial (CPU0) segment table
+ * 0x7000 - 0x7fff : FWNMI data area
+ * 0x8000 -        : Early init and support code
+ */
+
+
+/*
+ *   SPRG Usage
+ *
+ *   Register	Definition
+ *
+ *   SPRG0	reserved for hypervisor
+ *   SPRG1	temp - used to save gpr
+ *   SPRG2	temp - used to save gpr
+ *   SPRG3	virt addr of paca
+ */
+
+/*
+ * 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
+__start_interrupts:
+
+	STD_EXCEPTION_PSERIES(0x100, system_reset)
+
+	. = 0x200
+_machine_check_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+	. = 0x300
+	.globl data_access_pSeries
+data_access_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+BEGIN_FTR_SECTION
+	mtspr	SPRN_SPRG2,r12
+	mfspr	r13,SPRN_DAR
+	mfspr	r12,SPRN_DSISR
+	srdi	r13,r13,60
+	rlwimi	r13,r12,16,0x20
+	mfcr	r12
+	cmpwi	r13,0x2c
+	beq	do_stab_bolted_pSeries
+	mtcrf	0x80,r12
+	mfspr	r12,SPRN_SPRG2
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common)
+
+	. = 0x380
+	.globl data_access_slb_pSeries
+data_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_DAR
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	mfcr	r9
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	mfspr	r10,SPRN_SPRG1
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+#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)
+
+	. = 0x480
+	.globl instruction_access_slb_pSeries
+instruction_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	mfcr	r9
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	mfspr	r10,SPRN_SPRG1
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+#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)
+	STD_EXCEPTION_PSERIES(0x700, program_check)
+	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer)
+	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
+	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+
+	. = 0xc00
+	.globl	system_call_pSeries
+system_call_pSeries:
+	HMT_MEDIUM
+BEGIN_FTR_SECTION
+	cmpdi	r0,0x1ebe
+	beq-	1f
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
+	mr	r9,r13
+	mfspr	r13,SPRN_SPRG3
+	mfspr	r11,SPRN_SRR0
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	LOAD_HANDLER(r12, system_call_entry)
+	mtspr	SPRN_SRR0,r12
+	mfspr	r12,SPRN_SRR1
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
+/* Fast LE/BE switch system call */
+1:	mfspr	r12,SPRN_SRR1
+	xori	r12,r12,MSR_LE
+	mtspr	SPRN_SRR1,r12
+	rfid		/* return to userspace */
+	b	.
+
+	STD_EXCEPTION_PSERIES(0xd00, single_step)
+	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
+
+	/* We need to deal with the Altivec unavailable exception
+	 * here which is at 0xf20, thus in the middle of the
+	 * prolog code of the PerformanceMonitor one. A little
+	 * trickery is thus necessary
+	 */
+	. = 0xf00
+	b	performance_monitor_pSeries
+
+	. = 0xf20
+	b	altivec_unavailable_pSeries
+
+	. = 0xf40
+	b	vsx_unavailable_pSeries
+
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error)
+#endif /* CONFIG_CBE_RAS */
+	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance)
+#endif /* CONFIG_CBE_RAS */
+	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal)
+#endif /* CONFIG_CBE_RAS */
+
+	. = 0x3000
+
+/*** pSeries interrupt support ***/
+
+	/* moved from 0xf00 */
+	STD_EXCEPTION_PSERIES(., performance_monitor)
+	STD_EXCEPTION_PSERIES(., altivec_unavailable)
+	STD_EXCEPTION_PSERIES(., vsx_unavailable)
+
+/*
+ * An interrupt came in while soft-disabled; clear EE in SRR1,
+ * clear paca->hard_enabled and return.
+ */
+masked_interrupt:
+	stb	r10,PACAHARDIRQEN(r13)
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	mfspr	r10,SPRN_SRR1
+	rldicl	r10,r10,48,1		/* clear MSR_EE */
+	rotldi	r10,r10,16
+	mtspr	SPRN_SRR1,r10
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	mfspr	r13,SPRN_SPRG1
+	rfid
+	b	.
+
+	.align	7
+do_stab_bolted_pSeries:
+	mtcrf	0x80,r12
+	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__
+/*
+ * 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
+ */
+slb_miss_user_pseries:
+	std	r10,PACA_EXGEN+EX_R10(r13)
+	std	r11,PACA_EXGEN+EX_R11(r13)
+	std	r12,PACA_EXGEN+EX_R12(r13)
+	mfspr	r10,SPRG1
+	ld	r11,PACA_EXSLB+EX_R9(r13)
+	ld	r12,PACA_EXSLB+EX_R3(r13)
+	std	r10,PACA_EXGEN+EX_R13(r13)
+	std	r11,PACA_EXGEN+EX_R9(r13)
+	std	r12,PACA_EXGEN+EX_R3(r13)
+	clrrdi	r12,r13,32
+	mfmsr	r10
+	mfspr	r11,SRR0			/* save SRR0 */
+	ori	r12,r12,slb_miss_user_common@l	/* virt addr of handler */
+	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
+	mtspr	SRR0,r12
+	mfspr	r12,SRR1			/* and SRR1 */
+	mtspr	SRR1,r10
+	rfid
+	b	.				/* prevent spec. execution */
+#endif /* __DISABLED__ */
+
+	.align	7
+	.globl	__end_interrupts
+__end_interrupts:
+
+/*
+ * 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.
+ */
+
+/*** Common interrupt handlers ***/
+
+	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+
+	/*
+	 * Machine check is different because we use a different
+	 * save area: PACA_EXMC instead of PACA_EXGEN.
+	 */
+	.align	7
+	.globl machine_check_common
+machine_check_common:
+	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+	FINISH_NAP
+	DISABLE_INTS
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.machine_check_exception
+	b	.ret_from_except
+
+	STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
+	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
+	STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
+	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
+#ifdef CONFIG_ALTIVEC
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+#else
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+#endif
+#ifdef CONFIG_CBE_RAS
+	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
+	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
+	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,
+ * r10 contains the (bad) kernel stack pointer,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * We switch to using an emergency stack, save the registers there,
+ * and call kernel_bad_stack(), which panics.
+ */
+bad_stack:
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,64+INT_FRAME_SIZE
+	std	r9,_CCR(r1)
+	std	r10,GPR1(r1)
+	std	r11,_NIP(r1)
+	std	r12,_MSR(r1)
+	mfspr	r11,SPRN_DAR
+	mfspr	r12,SPRN_DSISR
+	std	r11,_DAR(r1)
+	std	r12,_DSISR(r1)
+	mflr	r10
+	mfctr	r11
+	mfxer	r12
+	std	r10,_LINK(r1)
+	std	r11,_CTR(r1)
+	std	r12,_XER(r1)
+	SAVE_GPR(0,r1)
+	SAVE_GPR(2,r1)
+	SAVE_4GPRS(3,r1)
+	SAVE_2GPRS(7,r1)
+	SAVE_10GPRS(12,r1)
+	SAVE_10GPRS(22,r1)
+	lhz	r12,PACA_TRAP_SAVE(r13)
+	std	r12,_TRAP(r1)
+	addi	r11,r1,INT_FRAME_SIZE
+	std	r11,0(r1)
+	li	r12,0
+	std	r12,0(r11)
+	ld	r2,PACATOC(r13)
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.kernel_bad_stack
+	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.
+ */
+	.align	7
+	.globl data_access_common
+data_access_common:
+	mfspr	r10,SPRN_DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,SPRN_DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	li	r5,0x300
+	b	.do_hash_page	 	/* Try to handle as hpte fault */
+
+	.align	7
+	.globl instruction_access_common
+instruction_access_common:
+	EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
+	ld	r3,_NIP(r1)
+	andis.	r4,r12,0x5820
+	li	r5,0x400
+	b	.do_hash_page		/* Try to handle as hpte fault */
+
+/*
+ * Here is the common SLB miss user that is used when going to virtual
+ * mode for SLB misses, that is currently not used
+ */
+#ifdef __DISABLED__
+	.align	7
+	.globl	slb_miss_user_common
+slb_miss_user_common:
+	mflr	r10
+	std	r3,PACA_EXGEN+EX_DAR(r13)
+	stw	r9,PACA_EXGEN+EX_CCR(r13)
+	std	r10,PACA_EXGEN+EX_LR(r13)
+	std	r11,PACA_EXGEN+EX_SRR0(r13)
+	bl	.slb_allocate_user
+
+	ld	r10,PACA_EXGEN+EX_LR(r13)
+	ld	r3,PACA_EXGEN+EX_R3(r13)
+	lwz	r9,PACA_EXGEN+EX_CCR(r13)
+	ld	r11,PACA_EXGEN+EX_SRR0(r13)
+	mtlr	r10
+	beq-	slb_miss_fault
+
+	andi.	r10,r12,MSR_RI		/* check for unrecoverable exception */
+	beq-	unrecov_user_slb
+	mfmsr	r10
+
+.machine push
+.machine "power4"
+	mtcrf	0x80,r9
+.machine pop
+
+	clrrdi	r10,r10,2		/* clear RI before setting SRR0/1 */
+	mtmsrd	r10,1
+
+	mtspr	SRR0,r11
+	mtspr	SRR1,r12
+
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	ld	r11,PACA_EXGEN+EX_R11(r13)
+	ld	r12,PACA_EXGEN+EX_R12(r13)
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	rfid
+	b	.
+
+slb_miss_fault:
+	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXGEN)
+	ld	r4,PACA_EXGEN+EX_DAR(r13)
+	li	r5,0
+	std	r4,_DAR(r1)
+	std	r5,_DSISR(r1)
+	b	handle_page_fault
+
+unrecov_user_slb:
+	EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
+	DISABLE_INTS
+	bl	.save_nvgprs
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.unrecoverable_exception
+	b	1b
+
+#endif /* __DISABLED__ */
+
+
+/*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r12 contain the saved SRR1, SRR0 is still ready for return
+ * r3 has the faulting address
+ * r9 - r13 are saved in paca->exslb.
+ * r3 is saved in paca->slb_r3
+ * We assume we aren't going to take any exceptions during this procedure.
+ */
+_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 */
+
+	bl	.slb_allocate_realmode
+
+	/* All done -- return from exception. */
+
+	ld	r10,PACA_EXSLB+EX_LR(r13)
+	ld	r3,PACA_EXSLB+EX_R3(r13)
+	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
+#ifdef CONFIG_PPC_ISERIES
+BEGIN_FW_FTR_SECTION
+	ld	r11,PACALPPACAPTR(r13)
+	ld	r11,LPPACASRR0(r11)		/* get SRR0 value */
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
+#endif /* CONFIG_PPC_ISERIES */
+
+	mtlr	r10
+
+	andi.	r10,r12,MSR_RI	/* check for unrecoverable exception */
+	beq-	2f
+
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+#ifdef CONFIG_PPC_ISERIES
+BEGIN_FW_FTR_SECTION
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
+#endif /* CONFIG_PPC_ISERIES */
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	rfid
+	b	.	/* prevent speculative execution */
+
+2:
+#ifdef CONFIG_PPC_ISERIES
+BEGIN_FW_FTR_SECTION
+	b	unrecov_slb
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
+#endif /* CONFIG_PPC_ISERIES */
+	mfspr	r11,SPRN_SRR0
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10,unrecov_slb)
+	mtspr	SPRN_SRR0,r10
+	ld	r10,PACAKMSR(r13)
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.
+
+unrecov_slb:
+	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
+	DISABLE_INTS
+	bl	.save_nvgprs
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.unrecoverable_exception
+	b	1b
+
+	.align	7
+	.globl hardware_interrupt_common
+	.globl hardware_interrupt_entry
+hardware_interrupt_common:
+	EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
+	FINISH_NAP
+hardware_interrupt_entry:
+	DISABLE_INTS
+BEGIN_FTR_SECTION
+	bl	.ppc64_runlatch_on
+END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_IRQ
+	b	.ret_from_except_lite
+
+#ifdef CONFIG_PPC_970_NAP
+power4_fixup_nap:
+	andc	r9,r9,r10
+	std	r9,TI_LOCAL_FLAGS(r11)
+	ld	r10,_LINK(r1)		/* make idle task do the */
+	std	r10,_NIP(r1)		/* equivalent of a blr */
+	blr
+#endif
+
+	.align	7
+	.globl alignment_common
+alignment_common:
+	mfspr	r10,SPRN_DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,SPRN_DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN)
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	std	r3,_DAR(r1)
+	std	r4,_DSISR(r1)
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.alignment_exception
+	b	.ret_from_except
+
+	.align	7
+	.globl program_check_common
+program_check_common:
+	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.program_check_exception
+	b	.ret_from_except
+
+	.align	7
+	.globl fp_unavailable_common
+fp_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
+	bne	1f			/* if from user, just load it up */
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.kernel_fp_unavailable_exception
+	BUG_OPCODE
+1:	bl	.load_up_fpu
+	b	fast_exception_return
+
+	.align	7
+	.globl altivec_unavailable_common
+altivec_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN)
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	beq	1f
+	bl	.load_up_altivec
+	b	fast_exception_return
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	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
+
+
+/*
+ * Hash table stuff
+ */
+	.align	7
+_STATIC(do_hash_page)
+	std	r3,_DAR(r1)
+	std	r4,_DSISR(r1)
+
+	andis.	r0,r4,0xa450		/* weird error? */
+	bne-	handle_page_fault	/* if not, try to insert a HPTE */
+BEGIN_FTR_SECTION
+	andis.	r0,r4,0x0020		/* Is it a segment table fault? */
+	bne-	do_ste_alloc		/* If so handle it */
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+
+	/*
+	 * On iSeries, we soft-disable interrupts here, then
+	 * hard-enable interrupts so that the hash_page code can spin on
+	 * the hash_table_lock without problems on a shared processor.
+	 */
+	DISABLE_INTS
+
+	/*
+	 * Currently, trace_hardirqs_off() will be called by DISABLE_INTS
+	 * and will clobber volatile registers when irq tracing is enabled
+	 * so we need to reload them. It may be possible to be smarter here
+	 * and move the irq tracing elsewhere but let's keep it simple for
+	 * now
+	 */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	ld	r3,_DAR(r1)
+	ld	r4,_DSISR(r1)
+	ld	r5,_TRAP(r1)
+	ld	r12,_MSR(r1)
+	clrrdi	r5,r5,4
+#endif /* CONFIG_TRACE_IRQFLAGS */
+	/*
+	 * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
+	 * accessing a userspace segment (even from the kernel). We assume
+	 * kernel addresses always have the high bit set.
+	 */
+	rlwinm	r4,r4,32-25+9,31-9,31-9	/* DSISR_STORE -> _PAGE_RW */
+	rotldi	r0,r3,15		/* Move high bit into MSR_PR posn */
+	orc	r0,r12,r0		/* MSR_PR | ~high_bit */
+	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
+	ori	r4,r4,1			/* add _PAGE_PRESENT */
+	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
+
+	/*
+	 * r3 contains the faulting address
+	 * r4 contains the required access permissions
+	 * r5 contains the trap number
+	 *
+	 * at return r3 = 0 for success
+	 */
+	bl	.hash_page		/* build HPTE if possible */
+	cmpdi	r3,0			/* see if hash_page succeeded */
+
+BEGIN_FW_FTR_SECTION
+	/*
+	 * If we had interrupts soft-enabled at the point where the
+	 * DSI/ISI occurred, and an interrupt came in during hash_page,
+	 * handle it now.
+	 * We jump to ret_from_except_lite rather than fast_exception_return
+	 * because ret_from_except_lite will check for and handle pending
+	 * interrupts if necessary.
+	 */
+	beq	13f
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
+
+BEGIN_FW_FTR_SECTION
+	/*
+	 * Here we have interrupts hard-disabled, so it is sufficient
+	 * to restore paca->{soft,hard}_enable and get out.
+	 */
+	beq	fast_exc_return_irq	/* Return from exception on success */
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
+
+	/* For a hash failure, we don't bother re-enabling interrupts */
+	ble-	12f
+
+	/*
+	 * hash_page couldn't handle it, set soft interrupt enable back
+	 * to what it was before the trap.  Note that .raw_local_irq_restore
+	 * handles any interrupts pending at this point.
+	 */
+	ld	r3,SOFTE(r1)
+	TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
+	bl	.raw_local_irq_restore
+	b	11f
+
+/* Here we have a page fault that hash_page can't handle. */
+handle_page_fault:
+	ENABLE_INTS
+11:	ld	r4,_DAR(r1)
+	ld	r5,_DSISR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_page_fault
+	cmpdi	r3,0
+	beq+	13f
+	bl	.save_nvgprs
+	mr	r5,r3
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lwz	r4,_DAR(r1)
+	bl	.bad_page_fault
+	b	.ret_from_except
+
+13:	b	.ret_from_except_lite
+
+/* We have a page fault that hash_page could handle but HV refused
+ * the PTE insertion
+ */
+12:	bl	.save_nvgprs
+	mr	r5,r3
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ld	r4,_DAR(r1)
+	bl	.low_hash_fault
+	b	.ret_from_except
+
+	/* here we have a segment miss */
+do_ste_alloc:
+	bl	.ste_allocate		/* try to insert stab entry */
+	cmpdi	r3,0
+	bne-	handle_page_fault
+	b	fast_exception_return
+
+/*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * r9 - r13 are saved in paca->exslb.
+ * We assume we aren't going to take any exceptions during this procedure.
+ * We assume (DAR >> 60) == 0xc.
+ */
+	.align	7
+_GLOBAL(do_stab_bolted)
+	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
+	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
+
+	/* Hash to the primary group */
+	ld	r10,PACASTABVIRT(r13)
+	mfspr	r11,SPRN_DAR
+	srdi	r11,r11,28
+	rldimi	r10,r11,7,52	/* r10 = first ste of the group */
+
+	/* Calculate VSID */
+	/* This is a kernel address, so protovsid = ESID */
+	ASM_VSID_SCRAMBLE(r11, r9, 256M)
+	rldic	r9,r11,12,16	/* r9 = vsid << 12 */
+
+	/* Search the primary group for a free entry */
+1:	ld	r11,0(r10)	/* Test valid bit of the current ste	*/
+	andi.	r11,r11,0x80
+	beq	2f
+	addi	r10,r10,16
+	andi.	r11,r10,0x70
+	bne	1b
+
+	/* Stick for only searching the primary group for now.		*/
+	/* At least for now, we use a very simple random castout scheme */
+	/* Use the TB as a random number ;  OR in 1 to avoid entry 0	*/
+	mftb	r11
+	rldic	r11,r11,4,57	/* r11 = (r11 << 4) & 0x70 */
+	ori	r11,r11,0x10
+
+	/* r10 currently points to an ste one past the group of interest */
+	/* make it point to the randomly selected entry			*/
+	subi	r10,r10,128
+	or 	r10,r10,r11	/* r10 is the entry to invalidate	*/
+
+	isync			/* mark the entry invalid		*/
+	ld	r11,0(r10)
+	rldicl	r11,r11,56,1	/* clear the valid bit */
+	rotldi	r11,r11,8
+	std	r11,0(r10)
+	sync
+
+	clrrdi	r11,r11,28	/* Get the esid part of the ste		*/
+	slbie	r11
+
+2:	std	r9,8(r10)	/* Store the vsid part of the ste	*/
+	eieio
+
+	mfspr	r11,SPRN_DAR		/* Get the new esid			*/
+	clrrdi	r11,r11,28	/* Permits a full 32b of ESID		*/
+	ori	r11,r11,0x90	/* Turn on valid and kp			*/
+	std	r11,0(r10)	/* Put new entry back into the stab	*/
+
+	sync
+
+	/* All done -- return from exception. */
+	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
+	ld	r11,PACA_EXSLB+EX_SRR0(r13)	/* get saved SRR0 */
+
+	andi.	r10,r12,MSR_RI
+	beq-	unrecov_slb
+
+	mtcrf	0x80,r9			/* restore CR */
+
+	mfmsr	r10
+	clrrdi	r10,r10,2
+	mtmsrd	r10,1
+
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	rfid
+	b	.	/* prevent speculative execution */
+
+/*
+ * Space for CPU0's segment table.
+ *
+ * On iSeries, the hypervisor must fill in at least one entry before
+ * we get control (with relocate on).  The address is given to the hv
+ * as a page number (see xLparMap below), so this must be at a
+ * fixed address (the linker can't compute (u64)&initial_stab >>
+ * PAGE_SHIFT).
+ */
+	. = STAB0_OFFSET	/* 0x6000 */
+	.globl initial_stab
+initial_stab:
+	.space	4096
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Data area reserved for FWNMI option.
+ * This address (0x7000) is fixed by the RPA.
+ */
+	.= 0x7000
+	.globl fwnmi_data_area
+fwnmi_data_area:
+#endif /* CONFIG_PPC_PSERIES */
+
+	/* iSeries does not use the FWNMI stuff, so it is safe to put
+	 * this here, even if we later allow kernels that will boot on
+	 * both pSeries and iSeries */
+#ifdef CONFIG_PPC_ISERIES
+        . = LPARMAP_PHYS
+	.globl xLparMap
+xLparMap:
+	.quad	HvEsidsToMap		/* xNumberEsids */
+	.quad	HvRangesToMap		/* xNumberRanges */
+	.quad	STAB0_PAGE		/* xSegmentTableOffs */
+	.zero	40			/* xRsvd */
+	/* xEsids (HvEsidsToMap entries of 2 quads) */
+	.quad	PAGE_OFFSET_ESID	/* xKernelEsid */
+	.quad	PAGE_OFFSET_VSID	/* xKernelVsid */
+	.quad	VMALLOC_START_ESID	/* xKernelEsid */
+	.quad	VMALLOC_START_VSID	/* xKernelVsid */
+	/* xRanges (HvRangesToMap entries of 3 quads) */
+	.quad	HvPagesToMap		/* xPages */
+	.quad	0			/* xOffset */
+	.quad	PAGE_OFFSET_VSID << (SID_SHIFT - HW_PAGE_SHIFT)	/* xVPN */
+
+#endif /* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_PPC_PSERIES
+        . = 0x8000
+#endif /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 2d182f1..1b12696 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -23,25 +23,14 @@
 #include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
-#ifdef CONFIG_PPC32
-# define GET_ADDR(addr) addr
-#else
-/* PowerPC64's functions are data that points to the functions */
-# define GET_ADDR(addr) (*(unsigned long *)addr)
-#endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-static unsigned int ftrace_nop_replace(void)
-{
-	return PPC_INST_NOP;
-}
-
 static unsigned int
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
 	unsigned int op;
 
-	addr = GET_ADDR(addr);
+	addr = ppc_function_entry((void *)addr);
 
 	/* if (link) set op to 'bl' else 'b' */
 	op = create_branch((unsigned int *)ip, addr, link ? 1 : 0);
@@ -49,14 +38,6 @@ ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 	return op;
 }
 
-#ifdef CONFIG_PPC64
-# define _ASM_ALIGN	" .align 3 "
-# define _ASM_PTR	" .llong "
-#else
-# define _ASM_ALIGN	" .align 2 "
-# define _ASM_PTR	" .long "
-#endif
-
 static int
 ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 {
@@ -197,7 +178,7 @@ __ftrace_make_nop(struct module *mod,
 	ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
 
 	/* This should match what was called */
-	if (ptr != GET_ADDR(addr)) {
+	if (ptr != ppc_function_entry((void *)addr)) {
 		printk(KERN_ERR "addr does not match %lx\n", ptr);
 		return -EINVAL;
 	}
@@ -328,7 +309,7 @@ int ftrace_make_nop(struct module *mod,
 	if (test_24bit_addr(ip, addr)) {
 		/* within range */
 		old = ftrace_call_replace(ip, addr, 1);
-		new = ftrace_nop_replace();
+		new = PPC_INST_NOP;
 		return ftrace_modify_code(ip, old, new);
 	}
 
@@ -466,7 +447,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 */
 	if (test_24bit_addr(ip, addr)) {
 		/* within range */
-		old = ftrace_nop_replace();
+		old = PPC_INST_NOP;
 		new = ftrace_call_replace(ip, addr, 1);
 		return ftrace_modify_code(ip, old, new);
 	}
@@ -570,7 +551,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return_hooker = (unsigned long)&mod_return_to_handler;
 #endif
 
-	return_hooker = GET_ADDR(return_hooker);
+	return_hooker = ppc_function_entry((void *)return_hooker);
 
 	/*
 	 * Protect against fault, even if it shouldn't
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index c01467f..4846946 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -733,9 +733,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 AltiVecUnavailable:
 	EXCEPTION_PROLOG
 #ifdef CONFIG_ALTIVEC
-	bne	load_up_altivec		/* if from user, just load it up */
+	beq	1f
+	bl	load_up_altivec		/* if from user, just load it up */
+	b	fast_exception_return
 #endif /* CONFIG_ALTIVEC */
-	addi	r3,r1,STACK_FRAME_OVERHEAD
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_EE_LITE(0xf20, altivec_unavailable_exception)
 
 PerformanceMonitor:
@@ -743,101 +745,6 @@ PerformanceMonitor:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0xf00, performance_monitor_exception)
 
-#ifdef CONFIG_ALTIVEC
-/* Note that the AltiVec support is closely modeled after the FP
- * support.  Changes to one are likely to be applicable to the
- * other!  */
-load_up_altivec:
-/*
- * Disable AltiVec for the task which had AltiVec previously,
- * and save its AltiVec registers in its thread_struct.
- * Enables AltiVec for use in the kernel on return.
- * On SMP we know the AltiVec units are free, since we give it up every
- * switch.  -- Kumar
- */
-	mfmsr	r5
-	oris	r5,r5,MSR_VEC@h
-	MTMSRD(r5)			/* enable use of AltiVec now */
-	isync
-/*
- * For SMP, we don't do lazy AltiVec switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_altivec in switch_to.
- */
-#ifndef CONFIG_SMP
-	tophys(r6,0)
-	addis	r3,r6,last_task_used_altivec@ha
-	lwz	r4,last_task_used_altivec@l(r3)
-	cmpwi	0,r4,0
-	beq	1f
-	add	r4,r4,r6
-	addi	r4,r4,THREAD	/* want THREAD of last_task_used_altivec */
-	SAVE_32VRS(0,r10,r4)
-	mfvscr	vr0
-	li	r10,THREAD_VSCR
-	stvx	vr0,r10,r4
-	lwz	r5,PT_REGS(r4)
-	add	r5,r5,r6
-	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r10,MSR_VEC@h
-	andc	r4,r4,r10	/* disable altivec for previous task */
-	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
-	/* enable use of AltiVec after return */
-	oris	r9,r9,MSR_VEC@h
-	mfspr	r5,SPRN_SPRG3		/* current task's THREAD (phys) */
-	li	r4,1
-	li	r10,THREAD_VSCR
-	stw	r4,THREAD_USED_VR(r5)
-	lvx	vr0,r10,r5
-	mtvscr	vr0
-	REST_32VRS(0,r10,r5)
-#ifndef CONFIG_SMP
-	subi	r4,r5,THREAD
-	sub	r4,r4,r6
-	stw	r4,last_task_used_altivec@l(r3)
-#endif /* CONFIG_SMP */
-	/* restore registers and return */
-	/* we haven't used ctr or xer or lr */
-	b	fast_exception_return
-
-/*
- * giveup_altivec(tsk)
- * Disable AltiVec for the task given as the argument,
- * and save the AltiVec registers in its thread_struct.
- * Enables AltiVec for use in the kernel on return.
- */
-
-	.globl	giveup_altivec
-giveup_altivec:
-	mfmsr	r5
-	oris	r5,r5,MSR_VEC@h
-	SYNC
-	MTMSRD(r5)			/* enable use of AltiVec now */
-	isync
-	cmpwi	0,r3,0
-	beqlr-				/* if no previous owner, done */
-	addi	r3,r3,THREAD		/* want THREAD of task */
-	lwz	r5,PT_REGS(r3)
-	cmpwi	0,r5,0
-	SAVE_32VRS(0, r4, r3)
-	mfvscr	vr0
-	li	r4,THREAD_VSCR
-	stvx	vr0,r4,r3
-	beq	1f
-	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r3,MSR_VEC@h
-	andc	r4,r4,r3		/* disable AltiVec for previous task */
-	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	lis	r4,last_task_used_altivec@ha
-	stw	r5,last_task_used_altivec@l(r4)
-#endif /* CONFIG_SMP */
-	blr
-#endif /* CONFIG_ALTIVEC */
 
 /*
  * This code is jumped to from the startup code to copy
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 50ef505..012505e 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -12,8 +12,9 @@
  *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
  *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
  *
- *  This file contains the low-level support and setup for the
- *  PowerPC-64 platform, including trap and interrupt dispatch.
+ *  This file contains the entry point for the 64-bit kernel along
+ *  with some early initialization code common to all 64-bit powerpc
+ *  variants.
  *
  *  This program is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
@@ -38,36 +39,25 @@
 #include <asm/exception.h>
 #include <asm/irqflags.h>
 
-/*
- * We layout physical memory as follows:
- * 0x0000 - 0x00ff : Secondary processor spin code
- * 0x0100 - 0x2fff : pSeries Interrupt prologs
- * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
- * 0x6000 - 0x6fff : Initial (CPU0) segment table
- * 0x7000 - 0x7fff : FWNMI data area
- * 0x8000 -        : Early init and support code
- */
-
-/*
- *   SPRG Usage
- *
- *   Register	Definition
- *
- *   SPRG0	reserved for hypervisor
- *   SPRG1	temp - used to save gpr
- *   SPRG2	temp - used to save gpr
- *   SPRG3	virt addr of paca
+/* The physical memory is layed out such that the secondary processor
+ * spin code sits at 0x0000...0x00ff. On server, the vectors follow
+ * using the layout described in exceptions-64s.S
  */
 
 /*
  * Entering into this code we make the following assumptions:
- *  For pSeries:
+ *
+ *  For pSeries or server processors:
  *   1. The MMU is off & open firmware is running in real mode.
  *   2. The kernel is entered at __start
  *
  *  For iSeries:
  *   1. The MMU is on (as it always is for iSeries)
  *   2. The kernel is entered at system_reset_iSeries
+ *
+ *  For Book3E processors:
+ *   1. The MMU is on running in AS0 in a state defined in ePAPR
+ *   2. The kernel is entered at __start
  */
 
 	.text
@@ -166,1065 +156,14 @@ exception_marker:
 	.text
 
 /*
- * 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
-__start_interrupts:
-
-	STD_EXCEPTION_PSERIES(0x100, system_reset)
-
-	. = 0x200
-_machine_check_pSeries:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
-
-	. = 0x300
-	.globl data_access_pSeries
-data_access_pSeries:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13
-BEGIN_FTR_SECTION
-	mtspr	SPRN_SPRG2,r12
-	mfspr	r13,SPRN_DAR
-	mfspr	r12,SPRN_DSISR
-	srdi	r13,r13,60
-	rlwimi	r13,r12,16,0x20
-	mfcr	r12
-	cmpwi	r13,0x2c
-	beq	do_stab_bolted_pSeries
-	mtcrf	0x80,r12
-	mfspr	r12,SPRN_SPRG2
-END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common)
-
-	. = 0x380
-	.globl data_access_slb_pSeries
-data_access_slb_pSeries:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13
-	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
-	std	r3,PACA_EXSLB+EX_R3(r13)
-	mfspr	r3,SPRN_DAR
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
-#ifdef __DISABLED__
-	/* Keep that around for when we re-implement dynamic VSIDs */
-	cmpdi	r3,0
-	bge	slb_miss_user_pseries
-#endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	mfspr	r10,SPRN_SPRG1
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-#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)
-
-	. = 0x480
-	.globl instruction_access_slb_pSeries
-instruction_access_slb_pSeries:
-	HMT_MEDIUM
-	mtspr	SPRN_SPRG1,r13
-	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
-	std	r3,PACA_EXSLB+EX_R3(r13)
-	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
-#ifdef __DISABLED__
-	/* Keep that around for when we re-implement dynamic VSIDs */
-	cmpdi	r3,0
-	bge	slb_miss_user_pseries
-#endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	mfspr	r10,SPRN_SPRG1
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-#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)
-	STD_EXCEPTION_PSERIES(0x700, program_check)
-	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
-	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer)
-	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
-	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
-
-	. = 0xc00
-	.globl	system_call_pSeries
-system_call_pSeries:
-	HMT_MEDIUM
-BEGIN_FTR_SECTION
-	cmpdi	r0,0x1ebe
-	beq-	1f
-END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
-	mr	r9,r13
-	mfspr	r13,SPRN_SPRG3
-	mfspr	r11,SPRN_SRR0
-	ld	r12,PACAKBASE(r13)
-	ld	r10,PACAKMSR(r13)
-	LOAD_HANDLER(r12, system_call_entry)
-	mtspr	SPRN_SRR0,r12
-	mfspr	r12,SPRN_SRR1
-	mtspr	SPRN_SRR1,r10
-	rfid
-	b	.	/* prevent speculative execution */
-
-/* Fast LE/BE switch system call */
-1:	mfspr	r12,SPRN_SRR1
-	xori	r12,r12,MSR_LE
-	mtspr	SPRN_SRR1,r12
-	rfid		/* return to userspace */
-	b	.
-
-	STD_EXCEPTION_PSERIES(0xd00, single_step)
-	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
-
-	/* We need to deal with the Altivec unavailable exception
-	 * here which is at 0xf20, thus in the middle of the
-	 * prolog code of the PerformanceMonitor one. A little
-	 * trickery is thus necessary
-	 */
-	. = 0xf00
-	b	performance_monitor_pSeries
-
-	. = 0xf20
-	b	altivec_unavailable_pSeries
-
-	. = 0xf40
-	b	vsx_unavailable_pSeries
-
-#ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error)
-#endif /* CONFIG_CBE_RAS */
-	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
-#ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance)
-#endif /* CONFIG_CBE_RAS */
-	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
-#ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal)
-#endif /* CONFIG_CBE_RAS */
-
-	. = 0x3000
-
-/*** pSeries interrupt support ***/
-
-	/* moved from 0xf00 */
-	STD_EXCEPTION_PSERIES(., performance_monitor)
-	STD_EXCEPTION_PSERIES(., altivec_unavailable)
-	STD_EXCEPTION_PSERIES(., vsx_unavailable)
-
-/*
- * An interrupt came in while soft-disabled; clear EE in SRR1,
- * clear paca->hard_enabled and return.
- */
-masked_interrupt:
-	stb	r10,PACAHARDIRQEN(r13)
-	mtcrf	0x80,r9
-	ld	r9,PACA_EXGEN+EX_R9(r13)
-	mfspr	r10,SPRN_SRR1
-	rldicl	r10,r10,48,1		/* clear MSR_EE */
-	rotldi	r10,r10,16
-	mtspr	SPRN_SRR1,r10
-	ld	r10,PACA_EXGEN+EX_R10(r13)
-	mfspr	r13,SPRN_SPRG1
-	rfid
-	b	.
-
-	.align	7
-do_stab_bolted_pSeries:
-	mtcrf	0x80,r12
-	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__
-/*
- * 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
- */
-slb_miss_user_pseries:
-	std	r10,PACA_EXGEN+EX_R10(r13)
-	std	r11,PACA_EXGEN+EX_R11(r13)
-	std	r12,PACA_EXGEN+EX_R12(r13)
-	mfspr	r10,SPRG1
-	ld	r11,PACA_EXSLB+EX_R9(r13)
-	ld	r12,PACA_EXSLB+EX_R3(r13)
-	std	r10,PACA_EXGEN+EX_R13(r13)
-	std	r11,PACA_EXGEN+EX_R9(r13)
-	std	r12,PACA_EXGEN+EX_R3(r13)
-	clrrdi	r12,r13,32
-	mfmsr	r10
-	mfspr	r11,SRR0			/* save SRR0 */
-	ori	r12,r12,slb_miss_user_common@l	/* virt addr of handler */
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
-	mtspr	SRR0,r12
-	mfspr	r12,SRR1			/* and SRR1 */
-	mtspr	SRR1,r10
-	rfid
-	b	.				/* prevent spec. execution */
-#endif /* __DISABLED__ */
-
-	.align	7
-	.globl	__end_interrupts
-__end_interrupts:
-
-/*
- * 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.
- */
-
-/*** Common interrupt handlers ***/
-
-	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
-
-	/*
-	 * Machine check is different because we use a different
-	 * save area: PACA_EXMC instead of PACA_EXGEN.
-	 */
-	.align	7
-	.globl machine_check_common
-machine_check_common:
-	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
-	FINISH_NAP
-	DISABLE_INTS
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_exception
-	b	.ret_from_except
-
-	STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
-	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
-	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-	STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
-	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
-#ifdef CONFIG_ALTIVEC
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
-#else
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
-#endif
-#ifdef CONFIG_CBE_RAS
-	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
-	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
-	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,
- * r10 contains the (bad) kernel stack pointer,
- * r11 and r12 contain the saved SRR0 and SRR1.
- * We switch to using an emergency stack, save the registers there,
- * and call kernel_bad_stack(), which panics.
- */
-bad_stack:
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,64+INT_FRAME_SIZE
-	std	r9,_CCR(r1)
-	std	r10,GPR1(r1)
-	std	r11,_NIP(r1)
-	std	r12,_MSR(r1)
-	mfspr	r11,SPRN_DAR
-	mfspr	r12,SPRN_DSISR
-	std	r11,_DAR(r1)
-	std	r12,_DSISR(r1)
-	mflr	r10
-	mfctr	r11
-	mfxer	r12
-	std	r10,_LINK(r1)
-	std	r11,_CTR(r1)
-	std	r12,_XER(r1)
-	SAVE_GPR(0,r1)
-	SAVE_GPR(2,r1)
-	SAVE_4GPRS(3,r1)
-	SAVE_2GPRS(7,r1)
-	SAVE_10GPRS(12,r1)
-	SAVE_10GPRS(22,r1)
-	lhz	r12,PACA_TRAP_SAVE(r13)
-	std	r12,_TRAP(r1)
-	addi	r11,r1,INT_FRAME_SIZE
-	std	r11,0(r1)
-	li	r12,0
-	std	r12,0(r11)
-	ld	r2,PACATOC(r13)
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_bad_stack
-	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.
- */
-	.align	7
-	.globl data_access_common
-data_access_common:
-	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
-	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
-	li	r5,0x300
-	b	.do_hash_page	 	/* Try to handle as hpte fault */
-
-	.align	7
-	.globl instruction_access_common
-instruction_access_common:
-	EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
-	ld	r3,_NIP(r1)
-	andis.	r4,r12,0x5820
-	li	r5,0x400
-	b	.do_hash_page		/* Try to handle as hpte fault */
-
-/*
- * Here is the common SLB miss user that is used when going to virtual
- * mode for SLB misses, that is currently not used
- */
-#ifdef __DISABLED__
-	.align	7
-	.globl	slb_miss_user_common
-slb_miss_user_common:
-	mflr	r10
-	std	r3,PACA_EXGEN+EX_DAR(r13)
-	stw	r9,PACA_EXGEN+EX_CCR(r13)
-	std	r10,PACA_EXGEN+EX_LR(r13)
-	std	r11,PACA_EXGEN+EX_SRR0(r13)
-	bl	.slb_allocate_user
-
-	ld	r10,PACA_EXGEN+EX_LR(r13)
-	ld	r3,PACA_EXGEN+EX_R3(r13)
-	lwz	r9,PACA_EXGEN+EX_CCR(r13)
-	ld	r11,PACA_EXGEN+EX_SRR0(r13)
-	mtlr	r10
-	beq-	slb_miss_fault
-
-	andi.	r10,r12,MSR_RI		/* check for unrecoverable exception */
-	beq-	unrecov_user_slb
-	mfmsr	r10
-
-.machine push
-.machine "power4"
-	mtcrf	0x80,r9
-.machine pop
-
-	clrrdi	r10,r10,2		/* clear RI before setting SRR0/1 */
-	mtmsrd	r10,1
-
-	mtspr	SRR0,r11
-	mtspr	SRR1,r12
-
-	ld	r9,PACA_EXGEN+EX_R9(r13)
-	ld	r10,PACA_EXGEN+EX_R10(r13)
-	ld	r11,PACA_EXGEN+EX_R11(r13)
-	ld	r12,PACA_EXGEN+EX_R12(r13)
-	ld	r13,PACA_EXGEN+EX_R13(r13)
-	rfid
-	b	.
-
-slb_miss_fault:
-	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXGEN)
-	ld	r4,PACA_EXGEN+EX_DAR(r13)
-	li	r5,0
-	std	r4,_DAR(r1)
-	std	r5,_DSISR(r1)
-	b	handle_page_fault
-
-unrecov_user_slb:
-	EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
-	DISABLE_INTS
-	bl	.save_nvgprs
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
-	b	1b
-
-#endif /* __DISABLED__ */
-
-
-/*
- * r13 points to the PACA, r9 contains the saved CR,
- * r12 contain the saved SRR1, SRR0 is still ready for return
- * r3 has the faulting address
- * r9 - r13 are saved in paca->exslb.
- * r3 is saved in paca->slb_r3
- * We assume we aren't going to take any exceptions during this procedure.
- */
-_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 */
-
-	bl	.slb_allocate_realmode
-
-	/* All done -- return from exception. */
-
-	ld	r10,PACA_EXSLB+EX_LR(r13)
-	ld	r3,PACA_EXSLB+EX_R3(r13)
-	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-	ld	r11,PACALPPACAPTR(r13)
-	ld	r11,LPPACASRR0(r11)		/* get SRR0 value */
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
-
-	mtlr	r10
-
-	andi.	r10,r12,MSR_RI	/* check for unrecoverable exception */
-	beq-	2f
-
-.machine	push
-.machine	"power4"
-	mtcrf	0x80,r9
-	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-.machine	pop
-
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-	mtspr	SPRN_SRR0,r11
-	mtspr	SPRN_SRR1,r12
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
-	ld	r9,PACA_EXSLB+EX_R9(r13)
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	ld	r11,PACA_EXSLB+EX_R11(r13)
-	ld	r12,PACA_EXSLB+EX_R12(r13)
-	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
-	b	.	/* prevent speculative execution */
-
-2:
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-	b	unrecov_slb
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
-	mfspr	r11,SPRN_SRR0
-	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10,unrecov_slb)
-	mtspr	SPRN_SRR0,r10
-	ld	r10,PACAKMSR(r13)
-	mtspr	SPRN_SRR1,r10
-	rfid
-	b	.
-
-unrecov_slb:
-	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
-	DISABLE_INTS
-	bl	.save_nvgprs
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
-	b	1b
-
-	.align	7
-	.globl hardware_interrupt_common
-	.globl hardware_interrupt_entry
-hardware_interrupt_common:
-	EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
-	FINISH_NAP
-hardware_interrupt_entry:
-	DISABLE_INTS
-BEGIN_FTR_SECTION
-	bl	.ppc64_runlatch_on
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_IRQ
-	b	.ret_from_except_lite
-
-#ifdef CONFIG_PPC_970_NAP
-power4_fixup_nap:
-	andc	r9,r9,r10
-	std	r9,TI_LOCAL_FLAGS(r11)
-	ld	r10,_LINK(r1)		/* make idle task do the */
-	std	r10,_NIP(r1)		/* equivalent of a blr */
-	blr
-#endif
-
-	.align	7
-	.globl alignment_common
-alignment_common:
-	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
-	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
-	bl	.alignment_exception
-	b	.ret_from_except
-
-	.align	7
-	.globl program_check_common
-program_check_common:
-	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
-	bl	.program_check_exception
-	b	.ret_from_except
-
-	.align	7
-	.globl fp_unavailable_common
-fp_unavailable_common:
-	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
-	bne	1f			/* if from user, just load it up */
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
-	bl	.kernel_fp_unavailable_exception
-	BUG_OPCODE
-1:	bl	.load_up_fpu
-	b	fast_exception_return
-
-	.align	7
-	.globl altivec_unavailable_common
-altivec_unavailable_common:
-	EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN)
-#ifdef CONFIG_ALTIVEC
-BEGIN_FTR_SECTION
-	beq	1f
-	bl	.load_up_altivec
-	b	fast_exception_return
-1:
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif
-	bl	.save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
-	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.
+ * On server, we include the exception vectors code here as it
+ * relies on absolute addressing which is only possible within
+ * this compilation unit
  */
-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:
+#ifdef CONFIG_PPC_BOOK3S
+#include "exceptions-64s.S"
 #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)
- * Disable VMX for the task which had it previously,
- * and save its vector registers in its thread_struct.
- * Enables the VMX for use in the kernel on return.
- * On SMP we know the VMX is free, since we give it up every
- * switch (ie, no lazy save of the vector registers).
- * On entry: r13 == 'current' && last_task_used_altivec != 'current'
- */
-_STATIC(load_up_altivec)
-	mfmsr	r5			/* grab the current MSR */
-	oris	r5,r5,MSR_VEC@h
-	mtmsrd	r5			/* enable use of VMX now */
-	isync
-
-/*
- * For SMP, we don't do lazy VMX switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_altvec in switch_to.
- * VRSAVE isn't dealt with here, that is done in the normal context
- * switch code. Note that we could rely on vrsave value to eventually
- * avoid saving all of the VREGs here...
- */
-#ifndef CONFIG_SMP
-	ld	r3,last_task_used_altivec@got(r2)
-	ld	r4,0(r3)
-	cmpdi	0,r4,0
-	beq	1f
-	/* Save VMX state to last_task_used_altivec's THREAD struct */
-	addi	r4,r4,THREAD
-	SAVE_32VRS(0,r5,r4)
-	mfvscr	vr0
-	li	r10,THREAD_VSCR
-	stvx	vr0,r10,r4
-	/* Disable VMX for last_task_used_altivec */
-	ld	r5,PT_REGS(r4)
-	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r6,MSR_VEC@h
-	andc	r4,r4,r6
-	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
-	/* Hack: if we get an altivec unavailable trap with VRSAVE
-	 * set to all zeros, we assume this is a broken application
-	 * that fails to set it properly, and thus we switch it to
-	 * all 1's
-	 */
-	mfspr	r4,SPRN_VRSAVE
-	cmpdi	0,r4,0
-	bne+	1f
-	li	r4,-1
-	mtspr	SPRN_VRSAVE,r4
-1:
-	/* enable use of VMX after return */
-	ld	r4,PACACURRENT(r13)
-	addi	r5,r4,THREAD		/* Get THREAD */
-	oris	r12,r12,MSR_VEC@h
-	std	r12,_MSR(r1)
-	li	r4,1
-	li	r10,THREAD_VSCR
-	stw	r4,THREAD_USED_VR(r5)
-	lvx	vr0,r10,r5
-	mtvscr	vr0
-	REST_32VRS(0,r4,r5)
-#ifndef CONFIG_SMP
-	/* Update last_task_used_math to 'current' */
-	subi	r4,r5,THREAD		/* Back to 'current' */
-	std	r4,0(r3)
-#endif /* CONFIG_SMP */
-	/* restore registers and return */
-	blr
-#endif /* CONFIG_ALTIVEC */
-
-#ifdef CONFIG_VSX
-/*
- * load_up_vsx(unused, unused, tsk)
- * Disable VSX for the task which had it previously,
- * and save its vector registers in its thread_struct.
- * Reuse the fp and vsx saves, but first check to see if they have
- * been saved already.
- * On entry: r13 == 'current' && last_task_used_vsx != 'current'
- */
-_STATIC(load_up_vsx)
-/* Load FP and VSX registers if they haven't been done yet */
-	andi.	r5,r12,MSR_FP
-	beql+	load_up_fpu		/* skip if already loaded */
-	andis.	r5,r12,MSR_VEC@h
-	beql+	load_up_altivec		/* skip if already loaded */
-
-#ifndef CONFIG_SMP
-	ld	r3,last_task_used_vsx@got(r2)
-	ld	r4,0(r3)
-	cmpdi	0,r4,0
-	beq	1f
-	/* Disable VSX for last_task_used_vsx */
-	addi	r4,r4,THREAD
-	ld	r5,PT_REGS(r4)
-	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r6,MSR_VSX@h
-	andc	r6,r4,r6
-	std	r6,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
-	ld	r4,PACACURRENT(r13)
-	addi	r4,r4,THREAD		/* Get THREAD */
-	li	r6,1
-	stw	r6,THREAD_USED_VSR(r4) /* ... also set thread used vsr */
-	/* enable use of VSX after return */
-	oris	r12,r12,MSR_VSX@h
-	std	r12,_MSR(r1)
-#ifndef CONFIG_SMP
-	/* Update last_task_used_math to 'current' */
-	ld	r4,PACACURRENT(r13)
-	std	r4,0(r3)
-#endif /* CONFIG_SMP */
-	b	fast_exception_return
-#endif /* CONFIG_VSX */
-
-/*
- * Hash table stuff
- */
-	.align	7
-_STATIC(do_hash_page)
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
-
-	andis.	r0,r4,0xa450		/* weird error? */
-	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-BEGIN_FTR_SECTION
-	andis.	r0,r4,0x0020		/* Is it a segment table fault? */
-	bne-	do_ste_alloc		/* If so handle it */
-END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
-
-	/*
-	 * On iSeries, we soft-disable interrupts here, then
-	 * hard-enable interrupts so that the hash_page code can spin on
-	 * the hash_table_lock without problems on a shared processor.
-	 */
-	DISABLE_INTS
-
-	/*
-	 * Currently, trace_hardirqs_off() will be called by DISABLE_INTS
-	 * and will clobber volatile registers when irq tracing is enabled
-	 * so we need to reload them. It may be possible to be smarter here
-	 * and move the irq tracing elsewhere but let's keep it simple for
-	 * now
-	 */
-#ifdef CONFIG_TRACE_IRQFLAGS
-	ld	r3,_DAR(r1)
-	ld	r4,_DSISR(r1)
-	ld	r5,_TRAP(r1)
-	ld	r12,_MSR(r1)
-	clrrdi	r5,r5,4
-#endif /* CONFIG_TRACE_IRQFLAGS */
-	/*
-	 * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
-	 * accessing a userspace segment (even from the kernel). We assume
-	 * kernel addresses always have the high bit set.
-	 */
-	rlwinm	r4,r4,32-25+9,31-9,31-9	/* DSISR_STORE -> _PAGE_RW */
-	rotldi	r0,r3,15		/* Move high bit into MSR_PR posn */
-	orc	r0,r12,r0		/* MSR_PR | ~high_bit */
-	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
-	ori	r4,r4,1			/* add _PAGE_PRESENT */
-	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
-
-	/*
-	 * r3 contains the faulting address
-	 * r4 contains the required access permissions
-	 * r5 contains the trap number
-	 *
-	 * at return r3 = 0 for success
-	 */
-	bl	.hash_page		/* build HPTE if possible */
-	cmpdi	r3,0			/* see if hash_page succeeded */
-
-BEGIN_FW_FTR_SECTION
-	/*
-	 * If we had interrupts soft-enabled at the point where the
-	 * DSI/ISI occurred, and an interrupt came in during hash_page,
-	 * handle it now.
-	 * We jump to ret_from_except_lite rather than fast_exception_return
-	 * because ret_from_except_lite will check for and handle pending
-	 * interrupts if necessary.
-	 */
-	beq	13f
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-
-BEGIN_FW_FTR_SECTION
-	/*
-	 * Here we have interrupts hard-disabled, so it is sufficient
-	 * to restore paca->{soft,hard}_enable and get out.
-	 */
-	beq	fast_exc_return_irq	/* Return from exception on success */
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
-
-	/* For a hash failure, we don't bother re-enabling interrupts */
-	ble-	12f
-
-	/*
-	 * hash_page couldn't handle it, set soft interrupt enable back
-	 * to what it was before the trap.  Note that .raw_local_irq_restore
-	 * handles any interrupts pending at this point.
-	 */
-	ld	r3,SOFTE(r1)
-	TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
-	bl	.raw_local_irq_restore
-	b	11f
-
-/* Here we have a page fault that hash_page can't handle. */
-handle_page_fault:
-	ENABLE_INTS
-11:	ld	r4,_DAR(r1)
-	ld	r5,_DSISR(r1)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_page_fault
-	cmpdi	r3,0
-	beq+	13f
-	bl	.save_nvgprs
-	mr	r5,r3
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	lwz	r4,_DAR(r1)
-	bl	.bad_page_fault
-	b	.ret_from_except
-
-13:	b	.ret_from_except_lite
-
-/* We have a page fault that hash_page could handle but HV refused
- * the PTE insertion
- */
-12:	bl	.save_nvgprs
-	mr	r5,r3
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ld	r4,_DAR(r1)
-	bl	.low_hash_fault
-	b	.ret_from_except
-
-	/* here we have a segment miss */
-do_ste_alloc:
-	bl	.ste_allocate		/* try to insert stab entry */
-	cmpdi	r3,0
-	bne-	handle_page_fault
-	b	fast_exception_return
-
-/*
- * r13 points to the PACA, r9 contains the saved CR,
- * r11 and r12 contain the saved SRR0 and SRR1.
- * r9 - r13 are saved in paca->exslb.
- * We assume we aren't going to take any exceptions during this procedure.
- * We assume (DAR >> 60) == 0xc.
- */
-	.align	7
-_GLOBAL(do_stab_bolted)
-	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
-	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
-
-	/* Hash to the primary group */
-	ld	r10,PACASTABVIRT(r13)
-	mfspr	r11,SPRN_DAR
-	srdi	r11,r11,28
-	rldimi	r10,r11,7,52	/* r10 = first ste of the group */
-
-	/* Calculate VSID */
-	/* This is a kernel address, so protovsid = ESID */
-	ASM_VSID_SCRAMBLE(r11, r9, 256M)
-	rldic	r9,r11,12,16	/* r9 = vsid << 12 */
-
-	/* Search the primary group for a free entry */
-1:	ld	r11,0(r10)	/* Test valid bit of the current ste	*/
-	andi.	r11,r11,0x80
-	beq	2f
-	addi	r10,r10,16
-	andi.	r11,r10,0x70
-	bne	1b
-
-	/* Stick for only searching the primary group for now.		*/
-	/* At least for now, we use a very simple random castout scheme */
-	/* Use the TB as a random number ;  OR in 1 to avoid entry 0	*/
-	mftb	r11
-	rldic	r11,r11,4,57	/* r11 = (r11 << 4) & 0x70 */
-	ori	r11,r11,0x10
-
-	/* r10 currently points to an ste one past the group of interest */
-	/* make it point to the randomly selected entry			*/
-	subi	r10,r10,128
-	or 	r10,r10,r11	/* r10 is the entry to invalidate	*/
-
-	isync			/* mark the entry invalid		*/
-	ld	r11,0(r10)
-	rldicl	r11,r11,56,1	/* clear the valid bit */
-	rotldi	r11,r11,8
-	std	r11,0(r10)
-	sync
-
-	clrrdi	r11,r11,28	/* Get the esid part of the ste		*/
-	slbie	r11
-
-2:	std	r9,8(r10)	/* Store the vsid part of the ste	*/
-	eieio
-
-	mfspr	r11,SPRN_DAR		/* Get the new esid			*/
-	clrrdi	r11,r11,28	/* Permits a full 32b of ESID		*/
-	ori	r11,r11,0x90	/* Turn on valid and kp			*/
-	std	r11,0(r10)	/* Put new entry back into the stab	*/
-
-	sync
-
-	/* All done -- return from exception. */
-	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
-	ld	r11,PACA_EXSLB+EX_SRR0(r13)	/* get saved SRR0 */
-
-	andi.	r10,r12,MSR_RI
-	beq-	unrecov_slb
-
-	mtcrf	0x80,r9			/* restore CR */
-
-	mfmsr	r10
-	clrrdi	r10,r10,2
-	mtmsrd	r10,1
-
-	mtspr	SPRN_SRR0,r11
-	mtspr	SPRN_SRR1,r12
-	ld	r9,PACA_EXSLB+EX_R9(r13)
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	ld	r11,PACA_EXSLB+EX_R11(r13)
-	ld	r12,PACA_EXSLB+EX_R12(r13)
-	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
-	b	.	/* prevent speculative execution */
-
-/*
- * Space for CPU0's segment table.
- *
- * On iSeries, the hypervisor must fill in at least one entry before
- * we get control (with relocate on).  The address is given to the hv
- * as a page number (see xLparMap below), so this must be at a
- * fixed address (the linker can't compute (u64)&initial_stab >>
- * PAGE_SHIFT).
- */
-	. = STAB0_OFFSET	/* 0x6000 */
-	.globl initial_stab
-initial_stab:
-	.space	4096
-
-#ifdef CONFIG_PPC_PSERIES
-/*
- * Data area reserved for FWNMI option.
- * This address (0x7000) is fixed by the RPA.
- */
-	.= 0x7000
-	.globl fwnmi_data_area
-fwnmi_data_area:
-#endif /* CONFIG_PPC_PSERIES */
-
-	/* iSeries does not use the FWNMI stuff, so it is safe to put
-	 * this here, even if we later allow kernels that will boot on
-	 * both pSeries and iSeries */
-#ifdef CONFIG_PPC_ISERIES
-        . = LPARMAP_PHYS
-	.globl xLparMap
-xLparMap:
-	.quad	HvEsidsToMap		/* xNumberEsids */
-	.quad	HvRangesToMap		/* xNumberRanges */
-	.quad	STAB0_PAGE		/* xSegmentTableOffs */
-	.zero	40			/* xRsvd */
-	/* xEsids (HvEsidsToMap entries of 2 quads) */
-	.quad	PAGE_OFFSET_ESID	/* xKernelEsid */
-	.quad	PAGE_OFFSET_VSID	/* xKernelVsid */
-	.quad	VMALLOC_START_ESID	/* xKernelEsid */
-	.quad	VMALLOC_START_VSID	/* xKernelVsid */
-	/* xRanges (HvRangesToMap entries of 3 quads) */
-	.quad	HvPagesToMap		/* xPages */
-	.quad	0			/* xOffset */
-	.quad	PAGE_OFFSET_VSID << (SID_SHIFT - HW_PAGE_SHIFT)	/* xVPN */
-
-#endif /* CONFIG_PPC_ISERIES */
-
-#ifdef CONFIG_PPC_PSERIES
-        . = 0x8000
-#endif /* CONFIG_PPC_PSERIES */
 
 /*
  * On pSeries and most other platforms, secondary processors spin
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 95f39f1..5f9febc 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -256,7 +256,7 @@ label:
 	 * off DE in the DSRR1 value and clearing the debug status.	      \
 	 */								      \
 	mfspr	r10,SPRN_DBSR;		/* check single-step/branch taken */  \
-	andis.	r10,r10,DBSR_IC@h;					      \
+	andis.	r10,r10,(DBSR_IC|DBSR_BT)@h;				      \
 	beq+	2f;							      \
 									      \
 	lis	r10,KERNELBASE@h;	/* check if exception in vectors */   \
@@ -271,7 +271,7 @@ label:
 									      \
 	/* here it looks like we got an inappropriate debug exception. */     \
 1:	rlwinm	r9,r9,0,~MSR_DE;	/* clear DE in the CDRR1 value */     \
-	lis	r10,DBSR_IC@h;		/* clear the IC event */	      \
+	lis	r10,(DBSR_IC|DBSR_BT)@h;	/* clear the IC event */      \
 	mtspr	SPRN_DBSR,r10;						      \
 	/* restore state and get out */					      \
 	lwz	r10,_CCR(r11);						      \
@@ -309,7 +309,7 @@ label:
 	 * off DE in the CSRR1 value and clearing the debug status.	      \
 	 */								      \
 	mfspr	r10,SPRN_DBSR;		/* check single-step/branch taken */  \
-	andis.	r10,r10,DBSR_IC@h;					      \
+	andis.	r10,r10,(DBSR_IC|DBSR_BT)@h;				      \
 	beq+	2f;							      \
 									      \
 	lis	r10,KERNELBASE@h;	/* check if exception in vectors */   \
@@ -317,14 +317,14 @@ label:
 	cmplw	r12,r10;						      \
 	blt+	2f;			/* addr below exception vectors */    \
 									      \
-	lis	r10,DebugCrit@h;						      \
+	lis	r10,DebugCrit@h;					      \
 	ori	r10,r10,DebugCrit@l;					      \
 	cmplw	r12,r10;						      \
 	bgt+	2f;			/* addr above exception vectors */    \
 									      \
 	/* here it looks like we got an inappropriate debug exception. */     \
 1:	rlwinm	r9,r9,0,~MSR_DE;	/* clear DE in the CSRR1 value */     \
-	lis	r10,DBSR_IC@h;		/* clear the IC event */	      \
+	lis	r10,(DBSR_IC|DBSR_BT)@h;	/* clear the IC event */      \
 	mtspr	SPRN_DBSR,r10;						      \
 	/* restore state and get out */					      \
 	lwz	r10,_CCR(r11);						      \
diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c
index 688b329..ffc4253 100644
--- a/arch/powerpc/kernel/init_task.c
+++ b/arch/powerpc/kernel/init_task.c
@@ -9,10 +9,6 @@
 
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-struct mm_struct init_mm = INIT_MM(init_mm);
-
-EXPORT_SYMBOL(init_mm);
-
 /*
  * Initial thread structure.
  *
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 844d3f8..f7f376e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -118,6 +118,7 @@ notrace void raw_local_irq_restore(unsigned long en)
 	if (!en)
 		return;
 
+#ifdef CONFIG_PPC_STD_MMU_64
 	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
 		/*
 		 * Do we need to disable preemption here?  Not really: in the
@@ -135,6 +136,7 @@ notrace void raw_local_irq_restore(unsigned long en)
 		if (local_paca->lppaca_ptr->int_dword.any_int)
 			iseries_handle_interrupts();
 	}
+#endif /* CONFIG_PPC_STD_MMU_64 */
 
 	if (test_perf_counter_pending()) {
 		clear_perf_counter_pending();
@@ -254,77 +256,84 @@ void fixup_irqs(cpumask_t map)
 }
 #endif
 
-void do_IRQ(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	unsigned int irq;
 #ifdef CONFIG_IRQSTACKS
+static inline void handle_one_irq(unsigned int irq)
+{
 	struct thread_info *curtp, *irqtp;
-#endif
+	unsigned long saved_sp_limit;
+	struct irq_desc *desc;
 
-	irq_enter();
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[smp_processor_id()];
+
+	if (curtp == irqtp) {
+		/* We're already on the irq stack, just handle it */
+		generic_handle_irq(irq);
+		return;
+	}
+
+	desc = irq_desc + irq;
+	saved_sp_limit = current->thread.ksp_limit;
+
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the softirq bits in preempt_count so that the
+	 * softirq checks work in the hardirq context. */
+	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
+			       (curtp->preempt_count & SOFTIRQ_MASK);
+
+	current->thread.ksp_limit = (unsigned long)irqtp +
+		_ALIGN_UP(sizeof(struct thread_info), 16);
+
+	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
+	current->thread.ksp_limit = saved_sp_limit;
+	irqtp->task = NULL;
+
+	/* Set any flag that may have been set on the
+	 * alternate stack
+	 */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+}
+#else
+static inline void handle_one_irq(unsigned int irq)
+{
+	generic_handle_irq(irq);
+}
+#endif
 
+static inline void check_stack_overflow(void)
+{
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
-	/* Debugging check for stack overflow: is there less than 2KB free? */
-	{
-		long sp;
+	long sp;
 
-		sp = __get_SP() & (THREAD_SIZE-1);
+	sp = __get_SP() & (THREAD_SIZE-1);
 
-		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-			printk("do_IRQ: stack overflow: %ld\n",
-				sp - sizeof(struct thread_info));
-			dump_stack();
-		}
+	/* check for stack overflow: is there less than 2KB free? */
+	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
+		printk("do_IRQ: stack overflow: %ld\n",
+			sp - sizeof(struct thread_info));
+		dump_stack();
 	}
 #endif
+}
 
-	/*
-	 * Every platform is required to implement ppc_md.get_irq.
-	 * This function will either return an irq number or NO_IRQ to
-	 * indicate there are no more pending.
-	 * The value NO_IRQ_IGNORE is for buggy hardware and means that this
-	 * IRQ has already been handled. -- Tom
-	 */
-	irq = ppc_md.get_irq();
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	unsigned int irq;
 
-	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) {
-#ifdef CONFIG_IRQSTACKS
-		/* Switch to the irq stack to handle this */
-		curtp = current_thread_info();
-		irqtp = hardirq_ctx[smp_processor_id()];
-		if (curtp != irqtp) {
-			struct irq_desc *desc = irq_desc + irq;
-			void *handler = desc->handle_irq;
-			unsigned long saved_sp_limit = current->thread.ksp_limit;
-			if (handler == NULL)
-				handler = &__do_IRQ;
-			irqtp->task = curtp->task;
-			irqtp->flags = 0;
-
-			/* Copy the softirq bits in preempt_count so that the
-			 * softirq checks work in the hardirq context.
-			 */
-			irqtp->preempt_count =
-				(irqtp->preempt_count & ~SOFTIRQ_MASK) |
-				(curtp->preempt_count & SOFTIRQ_MASK);
+	irq_enter();
 
-			current->thread.ksp_limit = (unsigned long)irqtp +
-				_ALIGN_UP(sizeof(struct thread_info), 16);
-			call_handle_irq(irq, desc, irqtp, handler);
-			current->thread.ksp_limit = saved_sp_limit;
-			irqtp->task = NULL;
+	check_stack_overflow();
 
+	irq = ppc_md.get_irq();
 
-			/* Set any flag that may have been set on the
-			 * alternate stack
-			 */
-			if (irqtp->flags)
-				set_bits(irqtp->flags, &curtp->flags);
-		} else
-#endif
-			generic_handle_irq(irq);
-	} else if (irq != NO_IRQ_IGNORE)
+	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
+		handle_one_irq(irq);
+	else if (irq != NO_IRQ_IGNORE)
 		/* That's not SMP safe ... but who cares ? */
 		ppc_spurious_interrupts++;
 
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 78b3f784..2419cc7 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -169,6 +169,9 @@ struct hvcall_ppp_data {
 	u8	unallocated_weight;
 	u16	active_procs_in_pool;
 	u16	active_system_procs;
+	u16	phys_platform_procs;
+	u32	max_proc_cap_avail;
+	u32	entitled_proc_cap_avail;
 };
 
 /*
@@ -190,13 +193,18 @@ struct hvcall_ppp_data {
  *            XX - Unallocated Variable Processor Capacity Weight.
  *              XXXX - Active processors in Physical Processor Pool.
  *                  XXXX  - Processors active on platform.
+ *  R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1
+ *	XXXX - Physical platform procs allocated to virtualization.
+ *	    XXXXXX - Max procs capacity % available to the partitions pool.
+ *	          XXXXXX - Entitled procs capacity % available to the
+ *			   partitions pool.
  */
 static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
 {
 	unsigned long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
 
-	rc = plpar_hcall(H_GET_PPP, retbuf);
+	rc = plpar_hcall9(H_GET_PPP, retbuf);
 
 	ppp_data->entitlement = retbuf[0];
 	ppp_data->unallocated_entitlement = retbuf[1];
@@ -210,6 +218,10 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
 	ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff;
 	ppp_data->active_system_procs = retbuf[3] & 0xffff;
 
+	ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8;
+	ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff;
+	ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff;
+
 	return rc;
 }
 
@@ -234,6 +246,8 @@ static unsigned h_pic(unsigned long *pool_idle_time,
 static void parse_ppp_data(struct seq_file *m)
 {
 	struct hvcall_ppp_data ppp_data;
+	struct device_node *root;
+	const int *perf_level;
 	int rc;
 
 	rc = h_get_ppp(&ppp_data);
@@ -267,6 +281,28 @@ static void parse_ppp_data(struct seq_file *m)
 	seq_printf(m, "capped=%d\n", ppp_data.capped);
 	seq_printf(m, "unallocated_capacity=%lld\n",
 		   ppp_data.unallocated_entitlement);
+
+	/* The last bits of information returned from h_get_ppp are only
+	 * valid if the ibm,partition-performance-parameters-level
+	 * property is >= 1.
+	 */
+	root = of_find_node_by_path("/");
+	if (root) {
+		perf_level = of_get_property(root,
+				"ibm,partition-performance-parameters-level",
+					     NULL);
+		if (perf_level && (*perf_level >= 1)) {
+			seq_printf(m,
+			    "physical_procs_allocated_to_virtualization=%d\n",
+				   ppp_data.phys_platform_procs);
+			seq_printf(m, "max_proc_capacity_available=%d\n",
+				   ppp_data.max_proc_cap_avail);
+			seq_printf(m, "entitled_proc_capacity_available=%d\n",
+				   ppp_data.entitled_proc_cap_avail);
+		}
+
+		of_node_put(root);
+	}
 }
 
 /**
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index b9530b2..a5cf9c1 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -457,98 +457,6 @@ _GLOBAL(disable_kernel_fp)
 	isync
 	blr
 
-#ifdef CONFIG_ALTIVEC
-
-#if 0 /* this has no callers for now */
-/*
- * disable_kernel_altivec()
- * Disable the VMX.
- */
-_GLOBAL(disable_kernel_altivec)
-	mfmsr	r3
-	rldicl	r0,r3,(63-MSR_VEC_LG),1
-	rldicl	r3,r0,(MSR_VEC_LG+1),0
-	mtmsrd	r3			/* disable use of VMX now */
-	isync
-	blr
-#endif /* 0 */
-
-/*
- * giveup_altivec(tsk)
- * Disable VMX for the task given as the argument,
- * and save the vector registers in its thread_struct.
- * Enables the VMX for use in the kernel on return.
- */
-_GLOBAL(giveup_altivec)
-	mfmsr	r5
-	oris	r5,r5,MSR_VEC@h
-	mtmsrd	r5			/* enable use of VMX now */
-	isync
-	cmpdi	0,r3,0
-	beqlr-				/* if no previous owner, done */
-	addi	r3,r3,THREAD		/* want THREAD of task */
-	ld	r5,PT_REGS(r3)
-	cmpdi	0,r5,0
-	SAVE_32VRS(0,r4,r3)
-	mfvscr	vr0
-	li	r4,THREAD_VSCR
-	stvx	vr0,r4,r3
-	beq	1f
-	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	lis	r3,(MSR_VEC|MSR_VSX)@h
-FTR_SECTION_ELSE
-	lis	r3,MSR_VEC@h
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
-#else
-	lis	r3,MSR_VEC@h
-#endif
-	andc	r4,r4,r3		/* disable FP for previous task */
-	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	ld	r4,last_task_used_altivec@got(r2)
-	std	r5,0(r4)
-#endif /* CONFIG_SMP */
-	blr
-
-#endif /* CONFIG_ALTIVEC */
-
-#ifdef CONFIG_VSX
-/*
- * __giveup_vsx(tsk)
- * Disable VSX for the task given as the argument.
- * Does NOT save vsx registers.
- * Enables the VSX for use in the kernel on return.
- */
-_GLOBAL(__giveup_vsx)
-	mfmsr	r5
-	oris	r5,r5,MSR_VSX@h
-	mtmsrd	r5			/* enable use of VSX now */
-	isync
-
-	cmpdi	0,r3,0
-	beqlr-				/* if no previous owner, done */
-	addi	r3,r3,THREAD		/* want THREAD of task */
-	ld	r5,PT_REGS(r3)
-	cmpdi	0,r5,0
-	beq	1f
-	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r3,MSR_VSX@h
-	andc	r4,r4,r3		/* disable VSX for previous task */
-	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	ld	r4,last_task_used_vsx@got(r2)
-	std	r5,0(r4)
-#endif /* CONFIG_SMP */
-	blr
-
-#endif /* CONFIG_VSX */
-
 /* kexec_wait(phys_cpu)
  *
  * wait for the flag to change, indicating this kernel is going away but
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index c744b32..e9962c7 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -18,6 +18,8 @@
  * field correctly */
 extern unsigned long __toc_start;
 
+#ifdef CONFIG_PPC_BOOK3S
+
 /*
  * The structure which the hypervisor knows about - this structure
  * should not cross a page boundary.  The vpa_init/register_vpa call
@@ -41,6 +43,10 @@ struct lppaca lppaca[] = {
 	},
 };
 
+#endif /* CONFIG_PPC_BOOK3S */
+
+#ifdef CONFIG_PPC_STD_MMU_64
+
 /*
  * 3 persistent SLBs are registered here.  The buffer will be zero
  * initially, hence will all be invaild until we actually write them.
@@ -52,6 +58,8 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = {
 	},
 };
 
+#endif /* CONFIG_PPC_STD_MMU_64 */
+
 /* The Paca is an array with one entry per processor.  Each contains an
  * lppaca, which contains the information shared between the
  * hypervisor and Linux.
@@ -77,15 +85,19 @@ void __init initialise_pacas(void)
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		struct paca_struct *new_paca = &paca[cpu];
 
+#ifdef CONFIG_PPC_BOOK3S
 		new_paca->lppaca_ptr = &lppaca[cpu];
+#endif
 		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;
+#ifdef CONFIG_PPC_STD_MMU_64
+		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
+#endif /* CONFIG_PPC_STD_MMU_64 */
 
 	}
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 4fee63c..5a56e97 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1505,7 +1505,7 @@ void __init pcibios_resource_survey(void)
  * rest of the code later, for now, keep it as-is as our main
  * resource allocation function doesn't deal with sub-trees yet.
  */
-void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
+void pcibios_claim_one_bus(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 	struct pci_bus *child_bus;
@@ -1533,7 +1533,6 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 	list_for_each_entry(child_bus, &bus->children, node)
 		pcibios_claim_one_bus(child_bus);
 }
-EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
 
 
 /* pcibios_finish_adding_to_bus
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index d473634..3ae1c66 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -33,7 +33,6 @@ int pcibios_assign_bus_offset = 1;
 
 void pcibios_make_OF_bus_map(void);
 
-static void fixup_broken_pcnet32(struct pci_dev* dev);
 static void fixup_cpc710_pci64(struct pci_dev* dev);
 #ifdef CONFIG_PPC_OF
 static u8* pci_to_OF_bus_map;
@@ -72,16 +71,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_res
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); 
 
 static void
-fixup_broken_pcnet32(struct pci_dev* dev)
-{
-	if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
-		dev->vendor = PCI_VENDOR_ID_AMD;
-		pci_write_config_word(dev, PCI_VENDOR_ID, PCI_VENDOR_ID_AMD);
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TRIDENT,	PCI_ANY_ID,			fixup_broken_pcnet32);
-
-static void
 fixup_cpc710_pci64(struct pci_dev* dev)
 {
 	/* Hide the PCI64 BARs from the kernel as their content doesn't
@@ -447,14 +436,6 @@ static int __init pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-/* the next one is stolen from the alpha port... */
-void __init
-pcibios_update_irq(struct pci_dev *dev, int irq)
-{
-	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
-	/* XXX FIXME - update OF device tree node interrupt property */
-}
-
 static struct pci_controller*
 pci_bus_to_hose(int bus)
 {
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 96edb6f..9e8902f 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -43,16 +43,6 @@ unsigned long pci_probe_only = 1;
 unsigned long pci_io_base = ISA_IO_BASE;
 EXPORT_SYMBOL(pci_io_base);
 
-static void fixup_broken_pcnet32(struct pci_dev* dev)
-{
-	if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
-		dev->vendor = PCI_VENDOR_ID_AMD;
-		pci_write_config_word(dev, PCI_VENDOR_ID, PCI_VENDOR_ID_AMD);
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TRIDENT, PCI_ANY_ID, fixup_broken_pcnet32);
-
-
 static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
 {
 	const u32 *prop;
@@ -430,6 +420,9 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	 * so flushing the hash table is the only sane way to make sure
 	 * that no hash entries are covering that removed bridge area
 	 * while still allowing other busses overlapping those pages
+	 *
+	 * Note: If we ever support P2P hotplug on Book3E, we'll have
+	 * to do an appropriate TLB flush here too
 	 */
 	if (bus->self) {
 		struct resource *res = bus->resource[0];
@@ -437,8 +430,10 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 		pr_debug("IO unmapping for PCI-PCI bridge %s\n",
 			 pci_name(bus->self));
 
+#ifdef CONFIG_PPC_STD_MMU_64
 		__flush_hash_table_range(&init_mm, res->start + _IO_BASE,
 					 res->end + _IO_BASE + 1);
+#endif
 		return 0;
 	}
 
@@ -511,7 +506,7 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	pr_debug("IO mapping for PHB %s\n", hose->dn->full_name);
 	pr_debug("  phys=0x%016llx, virt=0x%p (alloc=0x%p)\n",
 		 hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
-	pr_debug("  size=0x%016lx (alloc=0x%016lx)\n",
+	pr_debug("  size=0x%016llx (alloc=0x%016lx)\n",
 		 hose->pci_io_size, size_page);
 
 	/* Establish the mapping */
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 1c67de5..d5e36e5 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -27,7 +27,6 @@
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
 
@@ -35,7 +34,7 @@
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
  */
-static void * __devinit update_dn_pci_info(struct device_node *dn, void *data)
+void * __devinit update_dn_pci_info(struct device_node *dn, void *data)
 {
 	struct pci_controller *phb = data;
 	const int *type =
@@ -184,29 +183,6 @@ struct device_node *fetch_dev_dn(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(fetch_dev_dn);
 
-static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
-{
-	struct device_node *np = node;
-	struct pci_dn *pci = NULL;
-	int err = NOTIFY_OK;
-
-	switch (action) {
-	case PSERIES_RECONFIG_ADD:
-		pci = np->parent->data;
-		if (pci)
-			update_dn_pci_info(np, pci->phb);
-		break;
-	default:
-		err = NOTIFY_DONE;
-		break;
-	}
-	return err;
-}
-
-static struct notifier_block pci_dn_reconfig_nb = {
-	.notifier_call = pci_dn_reconfig_notifier,
-};
-
 /** 
  * pci_devs_phb_init - Initialize phbs and pci devs under them.
  * 
@@ -223,6 +199,4 @@ void __init pci_devs_phb_init(void)
 	/* This must be done first so the device nodes have valid pci info! */
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		pci_devs_phb_init_dynamic(phb);
-
-	pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7b44a33..3e7135bb 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -650,7 +650,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
 				_ALIGN_UP(sizeof(struct thread_info), 16);
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_STD_MMU_64
 	if (cpu_has_feature(CPU_FTR_SLB)) {
 		unsigned long sp_vsid;
 		unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index ce01ff2..d4405b9 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -585,7 +585,7 @@ static void __init check_cpu_pa_features(unsigned long node)
 		      ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
 }
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_STD_MMU_64
 static void __init check_cpu_slb_size(unsigned long node)
 {
 	u32 *slb_size_ptr;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 2f0e64b..ef6f649 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -44,10 +44,7 @@
 #include <asm/sections.h>
 #include <asm/machdep.h>
 
-#ifdef CONFIG_LOGO_LINUX_CLUT224
 #include <linux/linux_logo.h>
-extern const struct linux_logo logo_linux_clut224;
-#endif
 
 /*
  * Properties whose value is longer than this get excluded from our
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 3635be6..9fa2c7d 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -704,15 +704,34 @@ void user_enable_single_step(struct task_struct *task)
 
 	if (regs != NULL) {
 #if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+		task->thread.dbcr0 &= ~DBCR0_BT;
 		task->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC;
 		regs->msr |= MSR_DE;
 #else
+		regs->msr &= ~MSR_BE;
 		regs->msr |= MSR_SE;
 #endif
 	}
 	set_tsk_thread_flag(task, TIF_SINGLESTEP);
 }
 
+void user_enable_block_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+		task->thread.dbcr0 &= ~DBCR0_IC;
+		task->thread.dbcr0 = DBCR0_IDM | DBCR0_BT;
+		regs->msr |= MSR_DE;
+#else
+		regs->msr &= ~MSR_SE;
+		regs->msr |= MSR_BE;
+#endif
+	}
+	set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
 void user_disable_single_step(struct task_struct *task)
 {
 	struct pt_regs *regs = task->thread.regs;
@@ -726,10 +745,10 @@ void user_disable_single_step(struct task_struct *task)
 
 	if (regs != NULL) {
 #if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
-		task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_IDM);
+		task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
 		regs->msr &= ~MSR_DE;
 #else
-		regs->msr &= ~MSR_SE;
+		regs->msr &= ~(MSR_SE | MSR_BE);
 #endif
 	}
 	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 8869001..54e66da 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -93,10 +93,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 {
 	struct device_node *busdn, *dn;
 
-	if (bus->self)
-		busdn = pci_device_to_OF_node(bus->self);
-	else
-		busdn = bus->sysdata;	/* must be a phb */
+	busdn = pci_bus_to_OF_node(bus);
 
 	/* Search only direct children of the bus */
 	for (dn = busdn->child; dn; dn = dn->sibling) {
@@ -140,10 +137,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 {
 	struct device_node *busdn, *dn;
 
-	if (bus->self)
-		busdn = pci_device_to_OF_node(bus->self);
-	else
-		busdn = bus->sysdata;	/* must be a phb */
+	busdn = pci_bus_to_OF_node(bus);
 
 	/* Search only direct children of the bus */
 	for (dn = busdn->child; dn; dn = dn->sibling) {
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 9e1ca74..1d15424 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -39,6 +39,7 @@
 #include <asm/serial.h>
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
+#include <asm/swiotlb.h>
 
 #include "setup.h"
 
@@ -332,6 +333,11 @@ void __init setup_arch(char **cmdline_p)
 		ppc_md.setup_arch();
 	if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab);
 
+#ifdef CONFIG_SWIOTLB
+	if (ppc_swiotlb_enable)
+		swiotlb_init();
+#endif
+
 	paging_init();
 
 	/* Initialize the MMU context management stuff */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c410c60..1f68160 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -61,6 +61,7 @@
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 #include <asm/kexec.h>
+#include <asm/swiotlb.h>
 
 #include "setup.h"
 
@@ -417,12 +418,14 @@ void __init setup_system(void)
 	if (ppc64_caches.iline_size != 0x80)
 		printk("ppc64_caches.icache_line_size = 0x%x\n",
 		       ppc64_caches.iline_size);
+#ifdef CONFIG_PPC_STD_MMU_64
 	if (htab_address)
 		printk("htab_address                  = 0x%p\n", htab_address);
 	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
+#endif /* CONFIG_PPC_STD_MMU_64 */
 	if (PHYSICAL_START > 0)
-		printk("physical_start                = 0x%lx\n",
-		       PHYSICAL_START);
+		printk("physical_start                = 0x%llx\n",
+		       (unsigned long long)PHYSICAL_START);
 	printk("-----------------------------------------------------\n");
 
 	DBG(" <- setup_system()\n");
@@ -511,8 +514,9 @@ void __init setup_arch(char **cmdline_p)
 	irqstack_early_init();
 	emergency_stack_init();
 
+#ifdef CONFIG_PPC_STD_MMU_64
 	stabs_alloc();
-
+#endif
 	/* set up the bootmem stuff with available memory */
 	do_init_bootmem();
 	sparse_init();
@@ -524,6 +528,11 @@ void __init setup_arch(char **cmdline_p)
 	if (ppc_md.setup_arch)
 		ppc_md.setup_arch();
 
+#ifdef CONFIG_SWIOTLB
+	if (ppc_swiotlb_enable)
+		swiotlb_init();
+#endif
+
 	paging_init();
 	ppc64_boot_msg(0x15, "Setup Done");
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 48571ac..15391c2 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -52,6 +52,7 @@
 #include <linux/jiffies.h>
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
+#include <linux/delay.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -109,7 +110,7 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 static struct clock_event_device decrementer_clockevent = {
        .name           = "decrementer",
        .rating         = 200,
-       .shift          = 16,
+       .shift          = 0,	/* To be filled in */
        .mult           = 0,	/* To be filled in */
        .irq            = 0,
        .set_next_event = decrementer_set_next_event,
@@ -843,6 +844,22 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 		decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
+static void __init setup_clockevent_multiplier(unsigned long hz)
+{
+	u64 mult, shift = 32;
+
+	while (1) {
+		mult = div_sc(hz, NSEC_PER_SEC, shift);
+		if (mult && (mult >> 32UL) == 0UL)
+			break;
+
+		shift--;
+	}
+
+	decrementer_clockevent.shift = shift;
+	decrementer_clockevent.mult = mult;
+}
+
 static void register_decrementer_clockevent(int cpu)
 {
 	struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
@@ -860,8 +877,7 @@ static void __init init_decrementer_clockevent(void)
 {
 	int cpu = smp_processor_id();
 
-	decrementer_clockevent.mult = div_sc(ppc_tb_freq, NSEC_PER_SEC,
-					     decrementer_clockevent.shift);
+	setup_clockevent_multiplier(ppc_tb_freq);
 	decrementer_clockevent.max_delta_ns =
 		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
 	decrementer_clockevent.min_delta_ns =
@@ -1128,6 +1144,15 @@ void div128_by_32(u64 dividend_high, u64 dividend_low,
 
 }
 
+/* We don't need to calibrate delay, we use the CPU timebase for that */
+void calibrate_delay(void)
+{
+	/* Some generic code (such as spinlock debug) use loops_per_jiffy
+	 * as the number of __delay(1) in a jiffy, so make it so
+	 */
+	loops_per_jiffy = tb_ticks_per_jiffy;
+}
+
 static int __init rtc_init(void)
 {
 	struct platform_device *pdev;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 678fbff..6f0ae1a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -33,7 +33,9 @@
 #include <linux/backlight.h>
 #include <linux/bug.h>
 #include <linux/kdebug.h>
+#include <linux/debugfs.h>
 
+#include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -757,36 +759,44 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate the mfspr rD, PVR. */
 	if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
+		PPC_WARN_EMULATED(mfpvr);
 		rd = (instword >> 21) & 0x1f;
 		regs->gpr[rd] = mfspr(SPRN_PVR);
 		return 0;
 	}
 
 	/* Emulating the dcba insn is just a no-op.  */
-	if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA)
+	if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) {
+		PPC_WARN_EMULATED(dcba);
 		return 0;
+	}
 
 	/* Emulate the mcrxr insn.  */
 	if ((instword & PPC_INST_MCRXR_MASK) == PPC_INST_MCRXR) {
 		int shift = (instword >> 21) & 0x1c;
 		unsigned long msk = 0xf0000000UL >> shift;
 
+		PPC_WARN_EMULATED(mcrxr);
 		regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
 		regs->xer &= ~0xf0000000UL;
 		return 0;
 	}
 
 	/* Emulate load/store string insn. */
-	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING)
+	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
+		PPC_WARN_EMULATED(string);
 		return emulate_string_inst(regs, instword);
+	}
 
 	/* Emulate the popcntb (Population Count Bytes) instruction. */
 	if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
+		PPC_WARN_EMULATED(popcntb);
 		return emulate_popcntb_inst(regs, instword);
 	}
 
 	/* Emulate isel (Integer Select) instruction */
 	if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
+		PPC_WARN_EMULATED(isel);
 		return emulate_isel(regs, instword);
 	}
 
@@ -984,6 +994,8 @@ void SoftwareEmulation(struct pt_regs *regs)
 
 #ifdef CONFIG_MATH_EMULATION
 	errcode = do_mathemu(regs);
+	if (errcode >= 0)
+		PPC_WARN_EMULATED(math);
 
 	switch (errcode) {
 	case 0:
@@ -1005,6 +1017,9 @@ void SoftwareEmulation(struct pt_regs *regs)
 
 #elif defined(CONFIG_8XX_MINIMAL_FPEMU)
 	errcode = Soft_emulate_8xx(regs);
+	if (errcode >= 0)
+		PPC_WARN_EMULATED(8xx);
+
 	switch (errcode) {
 	case 0:
 		emulate_single_step(regs);
@@ -1026,7 +1041,34 @@ void SoftwareEmulation(struct pt_regs *regs)
 
 void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 {
-	if (debug_status & DBSR_IC) {	/* instruction completion */
+	/* Hack alert: On BookE, Branch Taken stops on the branch itself, while
+	 * on server, it stops on the target of the branch. In order to simulate
+	 * the server behaviour, we thus restart right away with a single step
+	 * instead of stopping here when hitting a BT
+	 */
+	if (debug_status & DBSR_BT) {
+		regs->msr &= ~MSR_DE;
+
+		/* Disable BT */
+		mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_BT);
+		/* Clear the BT event */
+		mtspr(SPRN_DBSR, DBSR_BT);
+
+		/* Do the single step trick only when coming from userspace */
+		if (user_mode(regs)) {
+			current->thread.dbcr0 &= ~DBCR0_BT;
+			current->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+			regs->msr |= MSR_DE;
+			return;
+		}
+
+		if (notify_die(DIE_SSTEP, "block_step", regs, 5,
+			       5, SIGTRAP) == NOTIFY_STOP) {
+			return;
+		}
+		if (debugger_sstep(regs))
+			return;
+	} else if (debug_status & DBSR_IC) { 	/* Instruction complete */
 		regs->msr &= ~MSR_DE;
 
 		/* Disable instruction completion */
@@ -1042,9 +1084,8 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 		if (debugger_sstep(regs))
 			return;
 
-		if (user_mode(regs)) {
-			current->thread.dbcr0 &= ~DBCR0_IC;
-		}
+		if (user_mode(regs))
+			current->thread.dbcr0 &= ~(DBCR0_IC);
 
 		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
 	} else if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
@@ -1088,6 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs)
 
 	flush_altivec_to_thread(current);
 
+	PPC_WARN_EMULATED(altivec);
 	err = emulate_altivec(regs);
 	if (err == 0) {
 		regs->nip += 4;		/* skip emulated instruction */
@@ -1286,3 +1328,79 @@ void kernel_bad_stack(struct pt_regs *regs)
 void __init trap_init(void)
 {
 }
+
+
+#ifdef CONFIG_PPC_EMULATED_STATS
+
+#define WARN_EMULATED_SETUP(type)	.type = { .name = #type }
+
+struct ppc_emulated ppc_emulated = {
+#ifdef CONFIG_ALTIVEC
+	WARN_EMULATED_SETUP(altivec),
+#endif
+	WARN_EMULATED_SETUP(dcba),
+	WARN_EMULATED_SETUP(dcbz),
+	WARN_EMULATED_SETUP(fp_pair),
+	WARN_EMULATED_SETUP(isel),
+	WARN_EMULATED_SETUP(mcrxr),
+	WARN_EMULATED_SETUP(mfpvr),
+	WARN_EMULATED_SETUP(multiple),
+	WARN_EMULATED_SETUP(popcntb),
+	WARN_EMULATED_SETUP(spe),
+	WARN_EMULATED_SETUP(string),
+	WARN_EMULATED_SETUP(unaligned),
+#ifdef CONFIG_MATH_EMULATION
+	WARN_EMULATED_SETUP(math),
+#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
+	WARN_EMULATED_SETUP(8xx),
+#endif
+#ifdef CONFIG_VSX
+	WARN_EMULATED_SETUP(vsx),
+#endif
+};
+
+u32 ppc_warn_emulated;
+
+void ppc_warn_emulated_print(const char *type)
+{
+	if (printk_ratelimit())
+		pr_warning("%s used emulated %s instruction\n", current->comm,
+			   type);
+}
+
+static int __init ppc_warn_emulated_init(void)
+{
+	struct dentry *dir, *d;
+	unsigned int i;
+	struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
+
+	if (!powerpc_debugfs_root)
+		return -ENODEV;
+
+	dir = debugfs_create_dir("emulated_instructions",
+				 powerpc_debugfs_root);
+	if (!dir)
+		return -ENOMEM;
+
+	d = debugfs_create_u32("do_warn", S_IRUGO | S_IWUSR, dir,
+			       &ppc_warn_emulated);
+	if (!d)
+		goto fail;
+
+	for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) {
+		d = debugfs_create_u32(entries[i].name, S_IRUGO | S_IWUSR, dir,
+				       (u32 *)&entries[i].val.counter);
+		if (!d)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
+}
+
+device_initcall(ppc_warn_emulated_init);
+
+#endif /* CONFIG_PPC_EMULATED_STATS */
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 49ac3d6..ef36cbbc 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -1,5 +1,215 @@
+#include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+
+/*
+ * load_up_altivec(unused, unused, tsk)
+ * Disable VMX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ * On SMP we know the VMX is free, since we give it up every
+ * switch (ie, no lazy save of the vector registers).
+ */
+_GLOBAL(load_up_altivec)
+	mfmsr	r5			/* grab the current MSR */
+	oris	r5,r5,MSR_VEC@h
+	MTMSRD(r5)			/* enable use of AltiVec now */
+	isync
+
+/*
+ * For SMP, we don't do lazy VMX switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another.  Instead we call giveup_altvec in switch_to.
+ * VRSAVE isn't dealt with here, that is done in the normal context
+ * switch code. Note that we could rely on vrsave value to eventually
+ * avoid saving all of the VREGs here...
+ */
+#ifndef CONFIG_SMP
+	LOAD_REG_ADDRBASE(r3, last_task_used_altivec)
+	toreal(r3)
+	PPC_LL	r4,ADDROFF(last_task_used_altivec)(r3)
+	PPC_LCMPI	0,r4,0
+	beq	1f
+
+	/* Save VMX state to last_task_used_altivec's THREAD struct */
+	toreal(r4)
+	addi	r4,r4,THREAD
+	SAVE_32VRS(0,r5,r4)
+	mfvscr	vr0
+	li	r10,THREAD_VSCR
+	stvx	vr0,r10,r4
+	/* Disable VMX for last_task_used_altivec */
+	PPC_LL	r5,PT_REGS(r4)
+	toreal(r5)
+	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r10,MSR_VEC@h
+	andc	r4,r4,r10
+	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+
+	/* Hack: if we get an altivec unavailable trap with VRSAVE
+	 * set to all zeros, we assume this is a broken application
+	 * that fails to set it properly, and thus we switch it to
+	 * all 1's
+	 */
+	mfspr	r4,SPRN_VRSAVE
+	cmpdi	0,r4,0
+	bne+	1f
+	li	r4,-1
+	mtspr	SPRN_VRSAVE,r4
+1:
+	/* enable use of VMX after return */
+#ifdef CONFIG_PPC32
+	mfspr	r5,SPRN_SPRG3		/* current task's THREAD (phys) */
+	oris	r9,r9,MSR_VEC@h
+#else
+	ld	r4,PACACURRENT(r13)
+	addi	r5,r4,THREAD		/* Get THREAD */
+	oris	r12,r12,MSR_VEC@h
+	std	r12,_MSR(r1)
+#endif
+	li	r4,1
+	li	r10,THREAD_VSCR
+	stw	r4,THREAD_USED_VR(r5)
+	lvx	vr0,r10,r5
+	mtvscr	vr0
+	REST_32VRS(0,r4,r5)
+#ifndef CONFIG_SMP
+	/* Update last_task_used_math to 'current' */
+	subi	r4,r5,THREAD		/* Back to 'current' */
+	fromreal(r4)
+	PPC_STL	r4,ADDROFF(last_task_used_math)(r3)
+#endif /* CONFIG_SMP */
+	/* restore registers and return */
+	blr
+
+/*
+ * giveup_altivec(tsk)
+ * Disable VMX for the task given as the argument,
+ * and save the vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ */
+_GLOBAL(giveup_altivec)
+	mfmsr	r5
+	oris	r5,r5,MSR_VEC@h
+	SYNC
+	MTMSRD(r5)			/* enable use of VMX now */
+	isync
+	PPC_LCMPI	0,r3,0
+	beqlr-				/* if no previous owner, done */
+	addi	r3,r3,THREAD		/* want THREAD of task */
+	PPC_LL	r5,PT_REGS(r3)
+	PPC_LCMPI	0,r5,0
+	SAVE_32VRS(0,r4,r3)
+	mfvscr	vr0
+	li	r4,THREAD_VSCR
+	stvx	vr0,r4,r3
+	beq	1f
+	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	lis	r3,(MSR_VEC|MSR_VSX)@h
+FTR_SECTION_ELSE
+	lis	r3,MSR_VEC@h
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#else
+	lis	r3,MSR_VEC@h
+#endif
+	andc	r4,r4,r3		/* disable FP for previous task */
+	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+	li	r5,0
+	LOAD_REG_ADDRBASE(r4,last_task_used_altivec)
+	PPC_STL	r5,ADDROFF(last_task_used_altivec)(r4)
+#endif /* CONFIG_SMP */
+	blr
+
+#ifdef CONFIG_VSX
+
+#ifdef CONFIG_PPC32
+#error This asm code isn't ready for 32-bit kernels
+#endif
+
+/*
+ * load_up_vsx(unused, unused, tsk)
+ * Disable VSX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Reuse the fp and vsx saves, but first check to see if they have
+ * been saved already.
+ */
+_GLOBAL(load_up_vsx)
+/* Load FP and VSX registers if they haven't been done yet */
+	andi.	r5,r12,MSR_FP
+	beql+	load_up_fpu		/* skip if already loaded */
+	andis.	r5,r12,MSR_VEC@h
+	beql+	load_up_altivec		/* skip if already loaded */
+
+#ifndef CONFIG_SMP
+	ld	r3,last_task_used_vsx@got(r2)
+	ld	r4,0(r3)
+	cmpdi	0,r4,0
+	beq	1f
+	/* Disable VSX for last_task_used_vsx */
+	addi	r4,r4,THREAD
+	ld	r5,PT_REGS(r4)
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r6,MSR_VSX@h
+	andc	r6,r4,r6
+	std	r6,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+	ld	r4,PACACURRENT(r13)
+	addi	r4,r4,THREAD		/* Get THREAD */
+	li	r6,1
+	stw	r6,THREAD_USED_VSR(r4) /* ... also set thread used vsr */
+	/* enable use of VSX after return */
+	oris	r12,r12,MSR_VSX@h
+	std	r12,_MSR(r1)
+#ifndef CONFIG_SMP
+	/* Update last_task_used_math to 'current' */
+	ld	r4,PACACURRENT(r13)
+	std	r4,0(r3)
+#endif /* CONFIG_SMP */
+	b	fast_exception_return
+
+/*
+ * __giveup_vsx(tsk)
+ * Disable VSX for the task given as the argument.
+ * Does NOT save vsx registers.
+ * Enables the VSX for use in the kernel on return.
+ */
+_GLOBAL(__giveup_vsx)
+	mfmsr	r5
+	oris	r5,r5,MSR_VSX@h
+	mtmsrd	r5			/* enable use of VSX now */
+	isync
+
+	cmpdi	0,r3,0
+	beqlr-				/* if no previous owner, done */
+	addi	r3,r3,THREAD		/* want THREAD of task */
+	ld	r5,PT_REGS(r3)
+	cmpdi	0,r5,0
+	beq	1f
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r3,MSR_VSX@h
+	andc	r4,r4,r3		/* disable VSX for previous task */
+	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+	li	r5,0
+	ld	r4,last_task_used_vsx@got(r2)
+	std	r5,0(r4)
+#endif /* CONFIG_SMP */
+	blr
+
+#endif /* CONFIG_VSX */
+
 
 /*
  * The routines below are in assembler so we can closely control the