Merge branch 'dmaengine' into async-tx-next

Conflicts:
	crypto/async_tx/async_xor.c
	drivers/dma/ioat/dma_v2.h
	drivers/dma/ioat/pci.c
	drivers/md/raid5.c

42 files changed, 6955 insertions, 1475 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 71901fbda4a..b73396b9390 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -4,6 +4,8 @@
 
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
 ifeq ($(CONFIG_PPC64),y)
 CFLAGS_prom_init.o	+= -mno-minimal-toc
 endif
@@ -36,7 +38,7 @@ 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 +84,7 @@ 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 $(pci64-y) \
@@ -94,6 +97,10 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_counter.o
+obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
+				   power5+-pmu.o power6-pmu.o power7-pmu.o
+obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
@@ -102,12 +109,14 @@ obj-y				+= iomap.o
 endif
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
+obj-$(CONFIG_PPC32)		+= $(obj32-y)
 
 ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 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
@@ -120,6 +129,7 @@ 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    $<
@@ -128,5 +138,6 @@ 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 5ffcfaa77d6..a5b632e52fa 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 1e40bc05394..561b6465231 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));
@@ -131,35 +129,31 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
-	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
-	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
+	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
 	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,
@@ -169,6 +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/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index 54f767e31a1..1e9949e6885 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -239,6 +239,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
 	ori	r11,r11,HID0_SGE | HID0_FOLD | HID0_BHTE
 	ori	r11,r11,HID0_LRSTK | HID0_BTIC
 	oris	r11,r11,HID0_DPM@h
+BEGIN_MMU_FTR_SECTION
+	oris	r11,r11,HID0_HIGH_BAT@h
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 BEGIN_FTR_SECTION
 	xori	r11,r11,HID0_BTIC
 END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC)
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index eb4b9adcedb..0adb50ad803 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -17,6 +17,40 @@
 #include <asm/cputable.h>
 #include <asm/ppc_asm.h>
 
+_GLOBAL(__e500_icache_setup)
+	mfspr	r0, SPRN_L1CSR1
+	andi.	r3, r0, L1CSR1_ICE
+	bnelr				/* Already enabled */
+	oris	r0, r0, L1CSR1_CPE@h
+	ori	r0, r0, (L1CSR1_ICFI | L1CSR1_ICLFR |  L1CSR1_ICE)
+	mtspr	SPRN_L1CSR1, r0		/* Enable I-Cache */
+	isync
+	blr
+
+_GLOBAL(__e500_dcache_setup)
+	mfspr	r0, SPRN_L1CSR0
+	andi.	r3, r0, L1CSR0_DCE
+	bnelr				/* Already enabled */
+	msync
+	isync
+	li	r0, 0
+	mtspr	SPRN_L1CSR0, r0		/* Disable */
+	msync
+	isync
+	li	r0, (L1CSR0_DCFI | L1CSR0_CLFC)
+	mtspr	SPRN_L1CSR0, r0		/* Invalidate */
+	isync
+1:	mfspr	r0, SPRN_L1CSR0
+	andi.	r3, r0, L1CSR0_CLFC
+	bne+	1b			/* Wait for lock bits reset */
+	oris	r0, r0, L1CSR0_CPE@h
+	ori	r0, r0, L1CSR0_DCE
+	msync
+	isync
+	mtspr	SPRN_L1CSR0, r0		/* Enable */
+	isync
+	blr
+
 _GLOBAL(__setup_cpu_e200)
 	/* enable dedicated debug exception handling resources (Debug APU) */
 	mfspr	r3,SPRN_HID0
@@ -25,7 +59,16 @@ _GLOBAL(__setup_cpu_e200)
 	b	__setup_e200_ivors
 _GLOBAL(__setup_cpu_e500v1)
 _GLOBAL(__setup_cpu_e500v2)
-	b	__setup_e500_ivors
+	mflr	r4
+	bl	__e500_icache_setup
+	bl	__e500_dcache_setup
+	bl	__setup_e500_ivors
+	mtlr	r4
+	blr
 _GLOBAL(__setup_cpu_e500mc)
-	b	__setup_e500mc_ivors
-
+	mflr	r4
+	bl	__e500_icache_setup
+	bl	__e500_dcache_setup
+	bl	__setup_e500mc_ivors
+	mtlr	r4
+	blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3e33fb933d9..4a24a2fc457 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 00000000000..68ccf11e4f1
--- /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 6b02793dc75..20a60d661ba 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/entry_64.S b/arch/powerpc/kernel/entry_64.S
index abfc3233047..43e073477c3 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
 
+#ifdef CONFIG_PERF_COUNTERS
+	/* check paca->perf_counter_pending if we're enabling ints */
+	lbz	r3,PACAPERFPEND(r13)
+	and.	r3,r3,r5
+	beq	27f
+	bl	.perf_counter_do_pending
+27:
+#endif /* CONFIG_PERF_COUNTERS */
+
 	/* extract EE bit and use it to restore paca->hard_enabled */
 	ld	r3,_MSR(r1)
 	rldicl	r4,r3,49,63		/* r0 = (r3 >> 15) & 1 */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
new file mode 100644
index 00000000000..eb898112e57
--- /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 2d182f119d1..ce1f3e44c24 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
@@ -605,7 +586,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) {
 		*parent = old;
 		return;
 	}
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index c01467f952d..48469463f89 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 50ef505b8fb..012505ebd9f 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 95f39f1e68d..5f9febc8d14 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 688b329800b..ffc4253fef5 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 8c1a4966867..f7f376ea7b1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -53,6 +53,7 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
+#include <linux/perf_counter.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -117,6 +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
@@ -134,6 +136,12 @@ 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();
+		perf_counter_do_pending();
+	}
 
 	/*
 	 * if (get_paca()->hard_enabled) return;
@@ -248,77 +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 78b3f7840ad..2419cc706ff 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 b9530b2395a..a5cf9c1356a 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/module.c b/arch/powerpc/kernel/module.c
index 43e7e3a7f13..477c663e014 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -43,8 +43,6 @@ void *module_alloc(unsigned long size)
 void module_free(struct module *mod, void *module_region)
 {
 	vfree(module_region);
-	/* FIXME: If module_region == mod->init_region, trim exception
-           table entries. */
 }
 
 static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
new file mode 100644
index 00000000000..75ff47fed7b
--- /dev/null
+++ b/arch/powerpc/kernel/mpc7450-pmu.c
@@ -0,0 +1,417 @@
+/*
+ * Performance counter support for MPC7450-family processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/string.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+#define N_COUNTER	6	/* Number of hardware counters */
+#define MAX_ALT		3	/* Maximum number of event alternative codes */
+
+/*
+ * Bits in event code for MPC7450 family
+ */
+#define PM_THRMULT_MSKS	0x40000
+#define PM_THRESH_SH	12
+#define PM_THRESH_MSK	0x3f
+#define PM_PMC_SH	8
+#define PM_PMC_MSK	7
+#define PM_PMCSEL_MSK	0x7f
+
+/*
+ * Classify events according to how specific their PMC requirements are.
+ * Result is:
+ *	0: can go on any PMC
+ *	1: can go on PMCs 1-4
+ *	2: can go on PMCs 1,2,4
+ *	3: can go on PMCs 1 or 2
+ *	4: can only go on one PMC
+ *	-1: event code is invalid
+ */
+#define N_CLASSES	5
+
+static int mpc7450_classify_event(u32 event)
+{
+	int pmc;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > N_COUNTER)
+			return -1;
+		return 4;
+	}
+	event &= PM_PMCSEL_MSK;
+	if (event <= 1)
+		return 0;
+	if (event <= 7)
+		return 1;
+	if (event <= 13)
+		return 2;
+	if (event <= 22)
+		return 3;
+	return -1;
+}
+
+/*
+ * Events using threshold and possible threshold scale:
+ *	code	scale?	name
+ *	11e	N	PM_INSTQ_EXCEED_CYC
+ *	11f	N	PM_ALTV_IQ_EXCEED_CYC
+ *	128	Y	PM_DTLB_SEARCH_EXCEED_CYC
+ *	12b	Y	PM_LD_MISS_EXCEED_L1_CYC
+ *	220	N	PM_CQ_EXCEED_CYC
+ *	30c	N	PM_GPR_RB_EXCEED_CYC
+ *	30d	?	PM_FPR_IQ_EXCEED_CYC ?
+ *	311	Y	PM_ITLB_SEARCH_EXCEED
+ *	410	N	PM_GPR_IQ_EXCEED_CYC
+ */
+
+/*
+ * Return use of threshold and threshold scale bits:
+ * 0 = uses neither, 1 = uses threshold, 2 = uses both
+ */
+static int mpc7450_threshold_use(u32 event)
+{
+	int pmc, sel;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	sel = event & PM_PMCSEL_MSK;
+	switch (pmc) {
+	case 1:
+		if (sel == 0x1e || sel == 0x1f)
+			return 1;
+		if (sel == 0x28 || sel == 0x2b)
+			return 2;
+		break;
+	case 2:
+		if (sel == 0x20)
+			return 1;
+		break;
+	case 3:
+		if (sel == 0xc || sel == 0xd)
+			return 1;
+		if (sel == 0x11)
+			return 2;
+		break;
+	case 4:
+		if (sel == 0x10)
+			return 1;
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Layout of constraint bits:
+ * 33222222222211111111110000000000
+ * 10987654321098765432109876543210
+ *  |<    ><  > < > < ><><><><><><>
+ *  TS TV   G4   G3  G2P6P5P4P3P2P1
+ *
+ * P1 - P6
+ *	0 - 11: Count of events needing PMC1 .. PMC6
+ *
+ * G2
+ *	12 - 14: Count of events needing PMC1 or PMC2
+ *
+ * G3
+ *	16 - 18: Count of events needing PMC1, PMC2 or PMC4
+ *
+ * G4
+ *	20 - 23: Count of events needing PMC1, PMC2, PMC3 or PMC4
+ *
+ * TV
+ *	24 - 29: Threshold value requested
+ *
+ * TS
+ *	30: Threshold scale value requested
+ */
+
+static u32 pmcbits[N_COUNTER][2] = {
+	{ 0x00844002, 0x00111001 },	/* PMC1 mask, value: P1,G2,G3,G4 */
+	{ 0x00844008, 0x00111004 },	/* PMC2: P2,G2,G3,G4 */
+	{ 0x00800020, 0x00100010 },	/* PMC3: P3,G4 */
+	{ 0x00840080, 0x00110040 },	/* PMC4: P4,G3,G4 */
+	{ 0x00000200, 0x00000100 },	/* PMC5: P5 */
+	{ 0x00000800, 0x00000400 }	/* PMC6: P6 */
+};
+
+static u32 classbits[N_CLASSES - 1][2] = {
+	{ 0x00000000, 0x00000000 },	/* class 0: no constraint */
+	{ 0x00800000, 0x00100000 },	/* class 1: G4 */
+	{ 0x00040000, 0x00010000 },	/* class 2: G3 */
+	{ 0x00004000, 0x00001000 },	/* class 3: G2 */
+};
+
+static int mpc7450_get_constraint(u64 event, unsigned long *maskp,
+				  unsigned long *valp)
+{
+	int pmc, class;
+	u32 mask, value;
+	int thresh, tuse;
+
+	class = mpc7450_classify_event(event);
+	if (class < 0)
+		return -1;
+	if (class == 4) {
+		pmc = ((unsigned int)event >> PM_PMC_SH) & PM_PMC_MSK;
+		mask  = pmcbits[pmc - 1][0];
+		value = pmcbits[pmc - 1][1];
+	} else {
+		mask  = classbits[class][0];
+		value = classbits[class][1];
+	}
+
+	tuse = mpc7450_threshold_use(event);
+	if (tuse) {
+		thresh = ((unsigned int)event >> PM_THRESH_SH) & PM_THRESH_MSK;
+		mask  |= 0x3f << 24;
+		value |= thresh << 24;
+		if (tuse == 2) {
+			mask |= 0x40000000;
+			if ((unsigned int)event & PM_THRMULT_MSKS)
+				value |= 0x40000000;
+		}
+	}
+
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x217, 0x317 },		/* PM_L1_DCACHE_MISS */
+	{ 0x418, 0x50f, 0x60f },	/* PM_SNOOP_RETRY */
+	{ 0x502, 0x602 },		/* PM_L2_HIT */
+	{ 0x503, 0x603 },		/* PM_L3_HIT */
+	{ 0x504, 0x604 },		/* PM_L2_ICACHE_MISS */
+	{ 0x505, 0x605 },		/* PM_L3_ICACHE_MISS */
+	{ 0x506, 0x606 },		/* PM_L2_DCACHE_MISS */
+	{ 0x507, 0x607 },		/* PM_L3_DCACHE_MISS */
+	{ 0x50a, 0x623 },		/* PM_LD_HIT_L3 */
+	{ 0x50b, 0x624 },		/* PM_ST_HIT_L3 */
+	{ 0x50d, 0x60d },		/* PM_L2_TOUCH_HIT */
+	{ 0x50e, 0x60e },		/* PM_L3_TOUCH_HIT */
+	{ 0x512, 0x612 },		/* PM_INT_LOCAL */
+	{ 0x513, 0x61d },		/* PM_L2_MISS */
+	{ 0x514, 0x61e },		/* PM_L3_MISS */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u32 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static int mpc7450_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	u32 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative((u32)event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != (u32)event)
+				alt[nalt++] = ae;
+		}
+	}
+	return nalt;
+}
+
+/*
+ * Bitmaps of which PMCs each class can use for classes 0 - 3.
+ * Bit i is set if PMC i+1 is usable.
+ */
+static const u8 classmap[N_CLASSES] = {
+	0x3f, 0x0f, 0x0b, 0x03, 0
+};
+
+/* Bit position and width of each PMCSEL field */
+static const int pmcsel_shift[N_COUNTER] = {
+	6,	0,	27,	22,	17,	11
+};
+static const u32 pmcsel_mask[N_COUNTER] = {
+	0x7f,	0x3f,	0x1f,	0x1f,	0x1f,	0x3f
+};
+
+/*
+ * Compute MMCR0/1/2 values for a set of events.
+ */
+static int mpc7450_compute_mmcr(u64 event[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[])
+{
+	u8 event_index[N_CLASSES][N_COUNTER];
+	int n_classevent[N_CLASSES];
+	int i, j, class, tuse;
+	u32 pmc_inuse = 0, pmc_avail;
+	u32 mmcr0 = 0, mmcr1 = 0, mmcr2 = 0;
+	u32 ev, pmc, thresh;
+
+	if (n_ev > N_COUNTER)
+		return -1;
+
+	/* First pass: count usage in each class */
+	for (i = 0; i < N_CLASSES; ++i)
+		n_classevent[i] = 0;
+	for (i = 0; i < n_ev; ++i) {
+		class = mpc7450_classify_event(event[i]);
+		if (class < 0)
+			return -1;
+		j = n_classevent[class]++;
+		event_index[class][j] = i;
+	}
+
+	/* Second pass: allocate PMCs from most specific event to least */
+	for (class = N_CLASSES - 1; class >= 0; --class) {
+		for (i = 0; i < n_classevent[class]; ++i) {
+			ev = event[event_index[class][i]];
+			if (class == 4) {
+				pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
+				if (pmc_inuse & (1 << (pmc - 1)))
+					return -1;
+			} else {
+				/* Find a suitable PMC */
+				pmc_avail = classmap[class] & ~pmc_inuse;
+				if (!pmc_avail)
+					return -1;
+				pmc = ffs(pmc_avail);
+			}
+			pmc_inuse |= 1 << (pmc - 1);
+
+			tuse = mpc7450_threshold_use(ev);
+			if (tuse) {
+				thresh = (ev >> PM_THRESH_SH) & PM_THRESH_MSK;
+				mmcr0 |= thresh << 16;
+				if (tuse == 2 && (ev & PM_THRMULT_MSKS))
+					mmcr2 = 0x80000000;
+			}
+			ev &= pmcsel_mask[pmc - 1];
+			ev <<= pmcsel_shift[pmc - 1];
+			if (pmc <= 2)
+				mmcr0 |= ev;
+			else
+				mmcr1 |= ev;
+			hwc[event_index[class][i]] = pmc - 1;
+		}
+	}
+
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr0 |= MMCR0_PMCnCE;
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcr2;
+	return 0;
+}
+
+/*
+ * Disable counting by a PMC.
+ * Note that the pmc argument is 0-based here, not 1-based.
+ */
+static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 1)
+		mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+	else
+		mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+}
+
+static int mpc7450_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 1,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 2,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x217, /* PM_L1_DCACHE_MISS */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x122, /* PM_BR_CMPL */
+	[PERF_COUNT_HW_BRANCH_MISSES] 		= 0x41c, /* PM_BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x225	},
+		[C(OP_WRITE)] = {	0,		0x227	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x129,		0x115	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0x634,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x312	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x223	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x122,		0x41c	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+struct power_pmu mpc7450_pmu = {
+	.name			= "MPC7450 family",
+	.n_counter		= N_COUNTER,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x00111555ul,
+	.test_adder		= 0x00301000ul,
+	.compute_mmcr		= mpc7450_compute_mmcr,
+	.get_constraint		= mpc7450_get_constraint,
+	.get_alternatives	= mpc7450_get_alternatives,
+	.disable_pmc		= mpc7450_disable_pmc,
+	.n_generic		= ARRAY_SIZE(mpc7450_generic_events),
+	.generic_events		= mpc7450_generic_events,
+	.cache_events		= &mpc7450_cache_events,
+};
+
+static int init_mpc7450_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450"))
+		return -ENODEV;
+
+	return register_power_pmu(&mpc7450_pmu);
+}
+
+arch_initcall(init_mpc7450_pmu);
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index c744b327bca..e9962c7f8a0 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 4fee63cb53f..5a56e97c5ac 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 d473634e39e..3ae1c666ff9 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 96edb6f8bab..9e8902fa14c 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 1c67de52e3c..d5e36e5dc7c 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/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
new file mode 100644
index 00000000000..809fdf94b95
--- /dev/null
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -0,0 +1,1306 @@
+/*
+ * Performance counter support - powerpc architecture code
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_counter.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/reg.h>
+#include <asm/pmc.h>
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/ptrace.h>
+
+struct cpu_hw_counters {
+	int n_counters;
+	int n_percpu;
+	int disabled;
+	int n_added;
+	int n_limited;
+	u8  pmcs_enabled;
+	struct perf_counter *counter[MAX_HWCOUNTERS];
+	u64 events[MAX_HWCOUNTERS];
+	unsigned int flags[MAX_HWCOUNTERS];
+	unsigned long mmcr[3];
+	struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS];
+	u8  limited_hwidx[MAX_LIMITED_HWCOUNTERS];
+};
+DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters);
+
+struct power_pmu *ppmu;
+
+/*
+ * Normally, to ignore kernel events we set the FCS (freeze counters
+ * in supervisor mode) bit in MMCR0, but if the kernel runs with the
+ * hypervisor bit set in the MSR, or if we are running on a processor
+ * where the hypervisor bit is forced to 1 (as on Apple G5 processors),
+ * then we need to use the FCHV bit to ignore kernel events.
+ */
+static unsigned int freeze_counters_kernel = MMCR0_FCS;
+
+/*
+ * 32-bit doesn't have MMCRA but does have an MMCR2,
+ * and a few other names are different.
+ */
+#ifdef CONFIG_PPC32
+
+#define MMCR0_FCHV		0
+#define MMCR0_PMCjCE		MMCR0_PMCnCE
+
+#define SPRN_MMCRA		SPRN_MMCR2
+#define MMCRA_SAMPLE_ENABLE	0
+
+static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
+{
+	return 0;
+}
+static inline void perf_set_pmu_inuse(int inuse) { }
+static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { }
+static inline u32 perf_get_misc_flags(struct pt_regs *regs)
+{
+	return 0;
+}
+static inline void perf_read_regs(struct pt_regs *regs) { }
+static inline int perf_intr_is_nmi(struct pt_regs *regs)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC32 */
+
+/*
+ * Things that are specific to 64-bit implementations.
+ */
+#ifdef CONFIG_PPC64
+
+static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
+{
+	unsigned long mmcra = regs->dsisr;
+
+	if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) {
+		unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT;
+		if (slot > 1)
+			return 4 * (slot - 1);
+	}
+	return 0;
+}
+
+static inline void perf_set_pmu_inuse(int inuse)
+{
+	get_lppaca()->pmcregs_in_use = inuse;
+}
+
+/*
+ * The user wants a data address recorded.
+ * If we're not doing instruction sampling, give them the SDAR
+ * (sampled data address).  If we are doing instruction sampling, then
+ * only give them the SDAR if it corresponds to the instruction
+ * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC
+ * bit in MMCRA.
+ */
+static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
+{
+	unsigned long mmcra = regs->dsisr;
+	unsigned long sdsync = (ppmu->flags & PPMU_ALT_SIPR) ?
+		POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC;
+
+	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
+		*addrp = mfspr(SPRN_SDAR);
+}
+
+static inline u32 perf_get_misc_flags(struct pt_regs *regs)
+{
+	unsigned long mmcra = regs->dsisr;
+
+	if (TRAP(regs) != 0xf00)
+		return 0;	/* not a PMU interrupt */
+
+	if (ppmu->flags & PPMU_ALT_SIPR) {
+		if (mmcra & POWER6_MMCRA_SIHV)
+			return PERF_EVENT_MISC_HYPERVISOR;
+		return (mmcra & POWER6_MMCRA_SIPR) ?
+			PERF_EVENT_MISC_USER : PERF_EVENT_MISC_KERNEL;
+	}
+	if (mmcra & MMCRA_SIHV)
+		return PERF_EVENT_MISC_HYPERVISOR;
+	return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
+		PERF_EVENT_MISC_KERNEL;
+}
+
+/*
+ * Overload regs->dsisr to store MMCRA so we only need to read it once
+ * on each interrupt.
+ */
+static inline void perf_read_regs(struct pt_regs *regs)
+{
+	regs->dsisr = mfspr(SPRN_MMCRA);
+}
+
+/*
+ * If interrupts were soft-disabled when a PMU interrupt occurs, treat
+ * it as an NMI.
+ */
+static inline int perf_intr_is_nmi(struct pt_regs *regs)
+{
+	return !regs->softe;
+}
+
+#endif /* CONFIG_PPC64 */
+
+static void perf_counter_interrupt(struct pt_regs *regs);
+
+void perf_counter_print_debug(void)
+{
+}
+
+/*
+ * Read one performance monitor counter (PMC).
+ */
+static unsigned long read_pmc(int idx)
+{
+	unsigned long val;
+
+	switch (idx) {
+	case 1:
+		val = mfspr(SPRN_PMC1);
+		break;
+	case 2:
+		val = mfspr(SPRN_PMC2);
+		break;
+	case 3:
+		val = mfspr(SPRN_PMC3);
+		break;
+	case 4:
+		val = mfspr(SPRN_PMC4);
+		break;
+	case 5:
+		val = mfspr(SPRN_PMC5);
+		break;
+	case 6:
+		val = mfspr(SPRN_PMC6);
+		break;
+#ifdef CONFIG_PPC64
+	case 7:
+		val = mfspr(SPRN_PMC7);
+		break;
+	case 8:
+		val = mfspr(SPRN_PMC8);
+		break;
+#endif /* CONFIG_PPC64 */
+	default:
+		printk(KERN_ERR "oops trying to read PMC%d\n", idx);
+		val = 0;
+	}
+	return val;
+}
+
+/*
+ * Write one PMC.
+ */
+static void write_pmc(int idx, unsigned long val)
+{
+	switch (idx) {
+	case 1:
+		mtspr(SPRN_PMC1, val);
+		break;
+	case 2:
+		mtspr(SPRN_PMC2, val);
+		break;
+	case 3:
+		mtspr(SPRN_PMC3, val);
+		break;
+	case 4:
+		mtspr(SPRN_PMC4, val);
+		break;
+	case 5:
+		mtspr(SPRN_PMC5, val);
+		break;
+	case 6:
+		mtspr(SPRN_PMC6, val);
+		break;
+#ifdef CONFIG_PPC64
+	case 7:
+		mtspr(SPRN_PMC7, val);
+		break;
+	case 8:
+		mtspr(SPRN_PMC8, val);
+		break;
+#endif /* CONFIG_PPC64 */
+	default:
+		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
+	}
+}
+
+/*
+ * Check if a set of events can all go on the PMU at once.
+ * If they can't, this will look at alternative codes for the events
+ * and see if any combination of alternative codes is feasible.
+ * The feasible set is returned in event[].
+ */
+static int power_check_constraints(u64 event[], unsigned int cflags[],
+				   int n_ev)
+{
+	unsigned long mask, value, nv;
+	u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	unsigned long amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	unsigned long avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	unsigned long smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS];
+	int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS];
+	int i, j;
+	unsigned long addf = ppmu->add_fields;
+	unsigned long tadd = ppmu->test_adder;
+
+	if (n_ev > ppmu->n_counter)
+		return -1;
+
+	/* First see if the events will go on as-is */
+	for (i = 0; i < n_ev; ++i) {
+		if ((cflags[i] & PPMU_LIMITED_PMC_REQD)
+		    && !ppmu->limited_pmc_event(event[i])) {
+			ppmu->get_alternatives(event[i], cflags[i],
+					       alternatives[i]);
+			event[i] = alternatives[i][0];
+		}
+		if (ppmu->get_constraint(event[i], &amasks[i][0],
+					 &avalues[i][0]))
+			return -1;
+	}
+	value = mask = 0;
+	for (i = 0; i < n_ev; ++i) {
+		nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf);
+		if ((((nv + tadd) ^ value) & mask) != 0 ||
+		    (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0)
+			break;
+		value = nv;
+		mask |= amasks[i][0];
+	}
+	if (i == n_ev)
+		return 0;	/* all OK */
+
+	/* doesn't work, gather alternatives... */
+	if (!ppmu->get_alternatives)
+		return -1;
+	for (i = 0; i < n_ev; ++i) {
+		choice[i] = 0;
+		n_alt[i] = ppmu->get_alternatives(event[i], cflags[i],
+						  alternatives[i]);
+		for (j = 1; j < n_alt[i]; ++j)
+			ppmu->get_constraint(alternatives[i][j],
+					     &amasks[i][j], &avalues[i][j]);
+	}
+
+	/* enumerate all possibilities and see if any will work */
+	i = 0;
+	j = -1;
+	value = mask = nv = 0;
+	while (i < n_ev) {
+		if (j >= 0) {
+			/* we're backtracking, restore context */
+			value = svalues[i];
+			mask = smasks[i];
+			j = choice[i];
+		}
+		/*
+		 * See if any alternative k for event i,
+		 * where k > j, will satisfy the constraints.
+		 */
+		while (++j < n_alt[i]) {
+			nv = (value | avalues[i][j]) +
+				(value & avalues[i][j] & addf);
+			if ((((nv + tadd) ^ value) & mask) == 0 &&
+			    (((nv + tadd) ^ avalues[i][j])
+			     & amasks[i][j]) == 0)
+				break;
+		}
+		if (j >= n_alt[i]) {
+			/*
+			 * No feasible alternative, backtrack
+			 * to event i-1 and continue enumerating its
+			 * alternatives from where we got up to.
+			 */
+			if (--i < 0)
+				return -1;
+		} else {
+			/*
+			 * Found a feasible alternative for event i,
+			 * remember where we got up to with this event,
+			 * go on to the next event, and start with
+			 * the first alternative for it.
+			 */
+			choice[i] = j;
+			svalues[i] = value;
+			smasks[i] = mask;
+			value = nv;
+			mask |= amasks[i][j];
+			++i;
+			j = -1;
+		}
+	}
+
+	/* OK, we have a feasible combination, tell the caller the solution */
+	for (i = 0; i < n_ev; ++i)
+		event[i] = alternatives[i][choice[i]];
+	return 0;
+}
+
+/*
+ * Check if newly-added counters have consistent settings for
+ * exclude_{user,kernel,hv} with each other and any previously
+ * added counters.
+ */
+static int check_excludes(struct perf_counter **ctrs, unsigned int cflags[],
+			  int n_prev, int n_new)
+{
+	int eu = 0, ek = 0, eh = 0;
+	int i, n, first;
+	struct perf_counter *counter;
+
+	n = n_prev + n_new;
+	if (n <= 1)
+		return 0;
+
+	first = 1;
+	for (i = 0; i < n; ++i) {
+		if (cflags[i] & PPMU_LIMITED_PMC_OK) {
+			cflags[i] &= ~PPMU_LIMITED_PMC_REQD;
+			continue;
+		}
+		counter = ctrs[i];
+		if (first) {
+			eu = counter->attr.exclude_user;
+			ek = counter->attr.exclude_kernel;
+			eh = counter->attr.exclude_hv;
+			first = 0;
+		} else if (counter->attr.exclude_user != eu ||
+			   counter->attr.exclude_kernel != ek ||
+			   counter->attr.exclude_hv != eh) {
+			return -EAGAIN;
+		}
+	}
+
+	if (eu || ek || eh)
+		for (i = 0; i < n; ++i)
+			if (cflags[i] & PPMU_LIMITED_PMC_OK)
+				cflags[i] |= PPMU_LIMITED_PMC_REQD;
+
+	return 0;
+}
+
+static void power_pmu_read(struct perf_counter *counter)
+{
+	s64 val, delta, prev;
+
+	if (!counter->hw.idx)
+		return;
+	/*
+	 * Performance monitor interrupts come even when interrupts
+	 * are soft-disabled, as long as interrupts are hard-enabled.
+	 * Therefore we treat them like NMIs.
+	 */
+	do {
+		prev = atomic64_read(&counter->hw.prev_count);
+		barrier();
+		val = read_pmc(counter->hw.idx);
+	} while (atomic64_cmpxchg(&counter->hw.prev_count, prev, val) != prev);
+
+	/* The counters are only 32 bits wide */
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &counter->count);
+	atomic64_sub(delta, &counter->hw.period_left);
+}
+
+/*
+ * On some machines, PMC5 and PMC6 can't be written, don't respect
+ * the freeze conditions, and don't generate interrupts.  This tells
+ * us if `counter' is using such a PMC.
+ */
+static int is_limited_pmc(int pmcnum)
+{
+	return (ppmu->flags & PPMU_LIMITED_PMC5_6)
+		&& (pmcnum == 5 || pmcnum == 6);
+}
+
+static void freeze_limited_counters(struct cpu_hw_counters *cpuhw,
+				    unsigned long pmc5, unsigned long pmc6)
+{
+	struct perf_counter *counter;
+	u64 val, prev, delta;
+	int i;
+
+	for (i = 0; i < cpuhw->n_limited; ++i) {
+		counter = cpuhw->limited_counter[i];
+		if (!counter->hw.idx)
+			continue;
+		val = (counter->hw.idx == 5) ? pmc5 : pmc6;
+		prev = atomic64_read(&counter->hw.prev_count);
+		counter->hw.idx = 0;
+		delta = (val - prev) & 0xfffffffful;
+		atomic64_add(delta, &counter->count);
+	}
+}
+
+static void thaw_limited_counters(struct cpu_hw_counters *cpuhw,
+				  unsigned long pmc5, unsigned long pmc6)
+{
+	struct perf_counter *counter;
+	u64 val;
+	int i;
+
+	for (i = 0; i < cpuhw->n_limited; ++i) {
+		counter = cpuhw->limited_counter[i];
+		counter->hw.idx = cpuhw->limited_hwidx[i];
+		val = (counter->hw.idx == 5) ? pmc5 : pmc6;
+		atomic64_set(&counter->hw.prev_count, val);
+		perf_counter_update_userpage(counter);
+	}
+}
+
+/*
+ * Since limited counters don't respect the freeze conditions, we
+ * have to read them immediately after freezing or unfreezing the
+ * other counters.  We try to keep the values from the limited
+ * counters as consistent as possible by keeping the delay (in
+ * cycles and instructions) between freezing/unfreezing and reading
+ * the limited counters as small and consistent as possible.
+ * Therefore, if any limited counters are in use, we read them
+ * both, and always in the same order, to minimize variability,
+ * and do it inside the same asm that writes MMCR0.
+ */
+static void write_mmcr0(struct cpu_hw_counters *cpuhw, unsigned long mmcr0)
+{
+	unsigned long pmc5, pmc6;
+
+	if (!cpuhw->n_limited) {
+		mtspr(SPRN_MMCR0, mmcr0);
+		return;
+	}
+
+	/*
+	 * Write MMCR0, then read PMC5 and PMC6 immediately.
+	 * To ensure we don't get a performance monitor interrupt
+	 * between writing MMCR0 and freezing/thawing the limited
+	 * counters, we first write MMCR0 with the counter overflow
+	 * interrupt enable bits turned off.
+	 */
+	asm volatile("mtspr %3,%2; mfspr %0,%4; mfspr %1,%5"
+		     : "=&r" (pmc5), "=&r" (pmc6)
+		     : "r" (mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)),
+		       "i" (SPRN_MMCR0),
+		       "i" (SPRN_PMC5), "i" (SPRN_PMC6));
+
+	if (mmcr0 & MMCR0_FC)
+		freeze_limited_counters(cpuhw, pmc5, pmc6);
+	else
+		thaw_limited_counters(cpuhw, pmc5, pmc6);
+
+	/*
+	 * Write the full MMCR0 including the counter overflow interrupt
+	 * enable bits, if necessary.
+	 */
+	if (mmcr0 & (MMCR0_PMC1CE | MMCR0_PMCjCE))
+		mtspr(SPRN_MMCR0, mmcr0);
+}
+
+/*
+ * Disable all counters to prevent PMU interrupts and to allow
+ * counters to be added or removed.
+ */
+void hw_perf_disable(void)
+{
+	struct cpu_hw_counters *cpuhw;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+
+	if (!cpuhw->disabled) {
+		cpuhw->disabled = 1;
+		cpuhw->n_added = 0;
+
+		/*
+		 * Check if we ever enabled the PMU on this cpu.
+		 */
+		if (!cpuhw->pmcs_enabled) {
+			if (ppc_md.enable_pmcs)
+				ppc_md.enable_pmcs();
+			cpuhw->pmcs_enabled = 1;
+		}
+
+		/*
+		 * Disable instruction sampling if it was enabled
+		 */
+		if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
+			mtspr(SPRN_MMCRA,
+			      cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+			mb();
+		}
+
+		/*
+		 * Set the 'freeze counters' bit.
+		 * The barrier is to make sure the mtspr has been
+		 * executed and the PMU has frozen the counters
+		 * before we return.
+		 */
+		write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC);
+		mb();
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Re-enable all counters if disable == 0.
+ * If we were previously disabled and counters were added, then
+ * put the new config on the PMU.
+ */
+void hw_perf_enable(void)
+{
+	struct perf_counter *counter;
+	struct cpu_hw_counters *cpuhw;
+	unsigned long flags;
+	long i;
+	unsigned long val;
+	s64 left;
+	unsigned int hwc_index[MAX_HWCOUNTERS];
+	int n_lim;
+	int idx;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	if (!cpuhw->disabled) {
+		local_irq_restore(flags);
+		return;
+	}
+	cpuhw->disabled = 0;
+
+	/*
+	 * If we didn't change anything, or only removed counters,
+	 * no need to recalculate MMCR* settings and reset the PMCs.
+	 * Just reenable the PMU with the current MMCR* settings
+	 * (possibly updated for removal of counters).
+	 */
+	if (!cpuhw->n_added) {
+		mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+		mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+		if (cpuhw->n_counters == 0)
+			perf_set_pmu_inuse(0);
+		goto out_enable;
+	}
+
+	/*
+	 * Compute MMCR* values for the new set of counters
+	 */
+	if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_counters, hwc_index,
+			       cpuhw->mmcr)) {
+		/* shouldn't ever get here */
+		printk(KERN_ERR "oops compute_mmcr failed\n");
+		goto out;
+	}
+
+	/*
+	 * Add in MMCR0 freeze bits corresponding to the
+	 * attr.exclude_* bits for the first counter.
+	 * We have already checked that all counters have the
+	 * same values for these bits as the first counter.
+	 */
+	counter = cpuhw->counter[0];
+	if (counter->attr.exclude_user)
+		cpuhw->mmcr[0] |= MMCR0_FCP;
+	if (counter->attr.exclude_kernel)
+		cpuhw->mmcr[0] |= freeze_counters_kernel;
+	if (counter->attr.exclude_hv)
+		cpuhw->mmcr[0] |= MMCR0_FCHV;
+
+	/*
+	 * Write the new configuration to MMCR* with the freeze
+	 * bit set and set the hardware counters to their initial values.
+	 * Then unfreeze the counters.
+	 */
+	perf_set_pmu_inuse(1);
+	mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+	mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+	mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
+				| MMCR0_FC);
+
+	/*
+	 * Read off any pre-existing counters that need to move
+	 * to another PMC.
+	 */
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (counter->hw.idx && counter->hw.idx != hwc_index[i] + 1) {
+			power_pmu_read(counter);
+			write_pmc(counter->hw.idx, 0);
+			counter->hw.idx = 0;
+		}
+	}
+
+	/*
+	 * Initialize the PMCs for all the new and moved counters.
+	 */
+	cpuhw->n_limited = n_lim = 0;
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (counter->hw.idx)
+			continue;
+		idx = hwc_index[i] + 1;
+		if (is_limited_pmc(idx)) {
+			cpuhw->limited_counter[n_lim] = counter;
+			cpuhw->limited_hwidx[n_lim] = idx;
+			++n_lim;
+			continue;
+		}
+		val = 0;
+		if (counter->hw.sample_period) {
+			left = atomic64_read(&counter->hw.period_left);
+			if (left < 0x80000000L)
+				val = 0x80000000L - left;
+		}
+		atomic64_set(&counter->hw.prev_count, val);
+		counter->hw.idx = idx;
+		write_pmc(idx, val);
+		perf_counter_update_userpage(counter);
+	}
+	cpuhw->n_limited = n_lim;
+	cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
+
+ out_enable:
+	mb();
+	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+
+	/*
+	 * Enable instruction sampling if necessary
+	 */
+	if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
+		mb();
+		mtspr(SPRN_MMCRA, cpuhw->mmcr[2]);
+	}
+
+ out:
+	local_irq_restore(flags);
+}
+
+static int collect_events(struct perf_counter *group, int max_count,
+			  struct perf_counter *ctrs[], u64 *events,
+			  unsigned int *flags)
+{
+	int n = 0;
+	struct perf_counter *counter;
+
+	if (!is_software_counter(group)) {
+		if (n >= max_count)
+			return -1;
+		ctrs[n] = group;
+		flags[n] = group->hw.counter_base;
+		events[n++] = group->hw.config;
+	}
+	list_for_each_entry(counter, &group->sibling_list, list_entry) {
+		if (!is_software_counter(counter) &&
+		    counter->state != PERF_COUNTER_STATE_OFF) {
+			if (n >= max_count)
+				return -1;
+			ctrs[n] = counter;
+			flags[n] = counter->hw.counter_base;
+			events[n++] = counter->hw.config;
+		}
+	}
+	return n;
+}
+
+static void counter_sched_in(struct perf_counter *counter, int cpu)
+{
+	counter->state = PERF_COUNTER_STATE_ACTIVE;
+	counter->oncpu = cpu;
+	counter->tstamp_running += counter->ctx->time - counter->tstamp_stopped;
+	if (is_software_counter(counter))
+		counter->pmu->enable(counter);
+}
+
+/*
+ * Called to enable a whole group of counters.
+ * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
+ * Assumes the caller has disabled interrupts and has
+ * frozen the PMU with hw_perf_save_disable.
+ */
+int hw_perf_group_sched_in(struct perf_counter *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx, int cpu)
+{
+	struct cpu_hw_counters *cpuhw;
+	long i, n, n0;
+	struct perf_counter *sub;
+
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	n0 = cpuhw->n_counters;
+	n = collect_events(group_leader, ppmu->n_counter - n0,
+			   &cpuhw->counter[n0], &cpuhw->events[n0],
+			   &cpuhw->flags[n0]);
+	if (n < 0)
+		return -EAGAIN;
+	if (check_excludes(cpuhw->counter, cpuhw->flags, n0, n))
+		return -EAGAIN;
+	i = power_check_constraints(cpuhw->events, cpuhw->flags, n + n0);
+	if (i < 0)
+		return -EAGAIN;
+	cpuhw->n_counters = n0 + n;
+	cpuhw->n_added += n;
+
+	/*
+	 * OK, this group can go on; update counter states etc.,
+	 * and enable any software counters
+	 */
+	for (i = n0; i < n0 + n; ++i)
+		cpuhw->counter[i]->hw.config = cpuhw->events[i];
+	cpuctx->active_oncpu += n;
+	n = 1;
+	counter_sched_in(group_leader, cpu);
+	list_for_each_entry(sub, &group_leader->sibling_list, list_entry) {
+		if (sub->state != PERF_COUNTER_STATE_OFF) {
+			counter_sched_in(sub, cpu);
+			++n;
+		}
+	}
+	ctx->nr_active += n;
+
+	return 1;
+}
+
+/*
+ * Add a counter to the PMU.
+ * If all counters are not already frozen, then we disable and
+ * re-enable the PMU in order to get hw_perf_enable to do the
+ * actual work of reconfiguring the PMU.
+ */
+static int power_pmu_enable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuhw;
+	unsigned long flags;
+	int n0;
+	int ret = -EAGAIN;
+
+	local_irq_save(flags);
+	perf_disable();
+
+	/*
+	 * Add the counter to the list (if there is room)
+	 * and check whether the total set is still feasible.
+	 */
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	n0 = cpuhw->n_counters;
+	if (n0 >= ppmu->n_counter)
+		goto out;
+	cpuhw->counter[n0] = counter;
+	cpuhw->events[n0] = counter->hw.config;
+	cpuhw->flags[n0] = counter->hw.counter_base;
+	if (check_excludes(cpuhw->counter, cpuhw->flags, n0, 1))
+		goto out;
+	if (power_check_constraints(cpuhw->events, cpuhw->flags, n0 + 1))
+		goto out;
+
+	counter->hw.config = cpuhw->events[n0];
+	++cpuhw->n_counters;
+	++cpuhw->n_added;
+
+	ret = 0;
+ out:
+	perf_enable();
+	local_irq_restore(flags);
+	return ret;
+}
+
+/*
+ * Remove a counter from the PMU.
+ */
+static void power_pmu_disable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuhw;
+	long i;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	perf_disable();
+
+	power_pmu_read(counter);
+
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		if (counter == cpuhw->counter[i]) {
+			while (++i < cpuhw->n_counters)
+				cpuhw->counter[i-1] = cpuhw->counter[i];
+			--cpuhw->n_counters;
+			ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr);
+			if (counter->hw.idx) {
+				write_pmc(counter->hw.idx, 0);
+				counter->hw.idx = 0;
+			}
+			perf_counter_update_userpage(counter);
+			break;
+		}
+	}
+	for (i = 0; i < cpuhw->n_limited; ++i)
+		if (counter == cpuhw->limited_counter[i])
+			break;
+	if (i < cpuhw->n_limited) {
+		while (++i < cpuhw->n_limited) {
+			cpuhw->limited_counter[i-1] = cpuhw->limited_counter[i];
+			cpuhw->limited_hwidx[i-1] = cpuhw->limited_hwidx[i];
+		}
+		--cpuhw->n_limited;
+	}
+	if (cpuhw->n_counters == 0) {
+		/* disable exceptions if no counters are running */
+		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
+	}
+
+	perf_enable();
+	local_irq_restore(flags);
+}
+
+/*
+ * Re-enable interrupts on a counter after they were throttled
+ * because they were coming too fast.
+ */
+static void power_pmu_unthrottle(struct perf_counter *counter)
+{
+	s64 val, left;
+	unsigned long flags;
+
+	if (!counter->hw.idx || !counter->hw.sample_period)
+		return;
+	local_irq_save(flags);
+	perf_disable();
+	power_pmu_read(counter);
+	left = counter->hw.sample_period;
+	counter->hw.last_period = left;
+	val = 0;
+	if (left < 0x80000000L)
+		val = 0x80000000L - left;
+	write_pmc(counter->hw.idx, val);
+	atomic64_set(&counter->hw.prev_count, val);
+	atomic64_set(&counter->hw.period_left, left);
+	perf_counter_update_userpage(counter);
+	perf_enable();
+	local_irq_restore(flags);
+}
+
+struct pmu power_pmu = {
+	.enable		= power_pmu_enable,
+	.disable	= power_pmu_disable,
+	.read		= power_pmu_read,
+	.unthrottle	= power_pmu_unthrottle,
+};
+
+/*
+ * Return 1 if we might be able to put counter on a limited PMC,
+ * or 0 if not.
+ * A counter can only go on a limited PMC if it counts something
+ * that a limited PMC can count, doesn't require interrupts, and
+ * doesn't exclude any processor mode.
+ */
+static int can_go_on_limited_pmc(struct perf_counter *counter, u64 ev,
+				 unsigned int flags)
+{
+	int n;
+	u64 alt[MAX_EVENT_ALTERNATIVES];
+
+	if (counter->attr.exclude_user
+	    || counter->attr.exclude_kernel
+	    || counter->attr.exclude_hv
+	    || counter->attr.sample_period)
+		return 0;
+
+	if (ppmu->limited_pmc_event(ev))
+		return 1;
+
+	/*
+	 * The requested event isn't on a limited PMC already;
+	 * see if any alternative code goes on a limited PMC.
+	 */
+	if (!ppmu->get_alternatives)
+		return 0;
+
+	flags |= PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD;
+	n = ppmu->get_alternatives(ev, flags, alt);
+
+	return n > 0;
+}
+
+/*
+ * Find an alternative event that goes on a normal PMC, if possible,
+ * and return the event code, or 0 if there is no such alternative.
+ * (Note: event code 0 is "don't count" on all machines.)
+ */
+static u64 normal_pmc_alternative(u64 ev, unsigned long flags)
+{
+	u64 alt[MAX_EVENT_ALTERNATIVES];
+	int n;
+
+	flags &= ~(PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD);
+	n = ppmu->get_alternatives(ev, flags, alt);
+	if (!n)
+		return 0;
+	return alt[0];
+}
+
+/* Number of perf_counters counting hardware events */
+static atomic_t num_counters;
+/* Used to avoid races in calling reserve/release_pmc_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/*
+ * Release the PMU if this is the last perf_counter.
+ */
+static void hw_perf_counter_destroy(struct perf_counter *counter)
+{
+	if (!atomic_add_unless(&num_counters, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_counters) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+/*
+ * Translate a generic cache event config to a raw event code.
+ */
+static int hw_perf_cache_event(u64 config, u64 *eventp)
+{
+	unsigned long type, op, result;
+	int ev;
+
+	if (!ppmu->cache_events)
+		return -EINVAL;
+
+	/* unpack config */
+	type = config & 0xff;
+	op = (config >> 8) & 0xff;
+	result = (config >> 16) & 0xff;
+
+	if (type >= PERF_COUNT_HW_CACHE_MAX ||
+	    op >= PERF_COUNT_HW_CACHE_OP_MAX ||
+	    result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	ev = (*ppmu->cache_events)[type][op][result];
+	if (ev == 0)
+		return -EOPNOTSUPP;
+	if (ev == -1)
+		return -EINVAL;
+	*eventp = ev;
+	return 0;
+}
+
+const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+{
+	u64 ev;
+	unsigned long flags;
+	struct perf_counter *ctrs[MAX_HWCOUNTERS];
+	u64 events[MAX_HWCOUNTERS];
+	unsigned int cflags[MAX_HWCOUNTERS];
+	int n;
+	int err;
+
+	if (!ppmu)
+		return ERR_PTR(-ENXIO);
+	switch (counter->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		ev = counter->attr.config;
+		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
+			return ERR_PTR(-EOPNOTSUPP);
+		ev = ppmu->generic_events[ev];
+		break;
+	case PERF_TYPE_HW_CACHE:
+		err = hw_perf_cache_event(counter->attr.config, &ev);
+		if (err)
+			return ERR_PTR(err);
+		break;
+	case PERF_TYPE_RAW:
+		ev = counter->attr.config;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+	counter->hw.config_base = ev;
+	counter->hw.idx = 0;
+
+	/*
+	 * If we are not running on a hypervisor, force the
+	 * exclude_hv bit to 0 so that we don't care what
+	 * the user set it to.
+	 */
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		counter->attr.exclude_hv = 0;
+
+	/*
+	 * If this is a per-task counter, then we can use
+	 * PM_RUN_* events interchangeably with their non RUN_*
+	 * equivalents, e.g. PM_RUN_CYC instead of PM_CYC.
+	 * XXX we should check if the task is an idle task.
+	 */
+	flags = 0;
+	if (counter->ctx->task)
+		flags |= PPMU_ONLY_COUNT_RUN;
+
+	/*
+	 * If this machine has limited counters, check whether this
+	 * event could go on a limited counter.
+	 */
+	if (ppmu->flags & PPMU_LIMITED_PMC5_6) {
+		if (can_go_on_limited_pmc(counter, ev, flags)) {
+			flags |= PPMU_LIMITED_PMC_OK;
+		} else if (ppmu->limited_pmc_event(ev)) {
+			/*
+			 * The requested event is on a limited PMC,
+			 * but we can't use a limited PMC; see if any
+			 * alternative goes on a normal PMC.
+			 */
+			ev = normal_pmc_alternative(ev, flags);
+			if (!ev)
+				return ERR_PTR(-EINVAL);
+		}
+	}
+
+	/*
+	 * If this is in a group, check if it can go on with all the
+	 * other hardware counters in the group.  We assume the counter
+	 * hasn't been linked into its leader's sibling list at this point.
+	 */
+	n = 0;
+	if (counter->group_leader != counter) {
+		n = collect_events(counter->group_leader, ppmu->n_counter - 1,
+				   ctrs, events, cflags);
+		if (n < 0)
+			return ERR_PTR(-EINVAL);
+	}
+	events[n] = ev;
+	ctrs[n] = counter;
+	cflags[n] = flags;
+	if (check_excludes(ctrs, cflags, n, 1))
+		return ERR_PTR(-EINVAL);
+	if (power_check_constraints(events, cflags, n + 1))
+		return ERR_PTR(-EINVAL);
+
+	counter->hw.config = events[n];
+	counter->hw.counter_base = cflags[n];
+	counter->hw.last_period = counter->hw.sample_period;
+	atomic64_set(&counter->hw.period_left, counter->hw.last_period);
+
+	/*
+	 * See if we need to reserve the PMU.
+	 * If no counters are currently in use, then we have to take a
+	 * mutex to ensure that we don't race with another task doing
+	 * reserve_pmc_hardware or release_pmc_hardware.
+	 */
+	err = 0;
+	if (!atomic_inc_not_zero(&num_counters)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_counters) == 0 &&
+		    reserve_pmc_hardware(perf_counter_interrupt))
+			err = -EBUSY;
+		else
+			atomic_inc(&num_counters);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	counter->destroy = hw_perf_counter_destroy;
+
+	if (err)
+		return ERR_PTR(err);
+	return &power_pmu;
+}
+
+/*
+ * A counter has overflowed; update its count and record
+ * things if requested.  Note that interrupts are hard-disabled
+ * here so there is no possibility of being interrupted.
+ */
+static void record_and_restart(struct perf_counter *counter, unsigned long val,
+			       struct pt_regs *regs, int nmi)
+{
+	u64 period = counter->hw.sample_period;
+	s64 prev, delta, left;
+	int record = 0;
+
+	/* we don't have to worry about interrupts here */
+	prev = atomic64_read(&counter->hw.prev_count);
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &counter->count);
+
+	/*
+	 * See if the total period for this counter has expired,
+	 * and update for the next period.
+	 */
+	val = 0;
+	left = atomic64_read(&counter->hw.period_left) - delta;
+	if (period) {
+		if (left <= 0) {
+			left += period;
+			if (left <= 0)
+				left = period;
+			record = 1;
+		}
+		if (left < 0x80000000LL)
+			val = 0x80000000LL - left;
+	}
+
+	/*
+	 * Finally record data if requested.
+	 */
+	if (record) {
+		struct perf_sample_data data = {
+			.regs	= regs,
+			.addr	= 0,
+			.period	= counter->hw.last_period,
+		};
+
+		if (counter->attr.sample_type & PERF_SAMPLE_ADDR)
+			perf_get_data_addr(regs, &data.addr);
+
+		if (perf_counter_overflow(counter, nmi, &data)) {
+			/*
+			 * Interrupts are coming too fast - throttle them
+			 * by setting the counter to 0, so it will be
+			 * at least 2^30 cycles until the next interrupt
+			 * (assuming each counter counts at most 2 counts
+			 * per cycle).
+			 */
+			val = 0;
+			left = ~0ULL >> 1;
+		}
+	}
+
+	write_pmc(counter->hw.idx, val);
+	atomic64_set(&counter->hw.prev_count, val);
+	atomic64_set(&counter->hw.period_left, left);
+	perf_counter_update_userpage(counter);
+}
+
+/*
+ * Called from generic code to get the misc flags (i.e. processor mode)
+ * for an event.
+ */
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	u32 flags = perf_get_misc_flags(regs);
+
+	if (flags)
+		return flags;
+	return user_mode(regs) ? PERF_EVENT_MISC_USER :
+		PERF_EVENT_MISC_KERNEL;
+}
+
+/*
+ * Called from generic code to get the instruction pointer
+ * for an event.
+ */
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	unsigned long ip;
+
+	if (TRAP(regs) != 0xf00)
+		return regs->nip;	/* not a PMU interrupt */
+
+	ip = mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
+	return ip;
+}
+
+/*
+ * Performance monitor interrupt stuff
+ */
+static void perf_counter_interrupt(struct pt_regs *regs)
+{
+	int i;
+	struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters);
+	struct perf_counter *counter;
+	unsigned long val;
+	int found = 0;
+	int nmi;
+
+	if (cpuhw->n_limited)
+		freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
+					mfspr(SPRN_PMC6));
+
+	perf_read_regs(regs);
+
+	nmi = perf_intr_is_nmi(regs);
+	if (nmi)
+		nmi_enter();
+	else
+		irq_enter();
+
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (!counter->hw.idx || is_limited_pmc(counter->hw.idx))
+			continue;
+		val = read_pmc(counter->hw.idx);
+		if ((int)val < 0) {
+			/* counter has overflowed */
+			found = 1;
+			record_and_restart(counter, val, regs, nmi);
+		}
+	}
+
+	/*
+	 * In case we didn't find and reset the counter that caused
+	 * the interrupt, scan all counters and reset any that are
+	 * negative, to avoid getting continual interrupts.
+	 * Any that we processed in the previous loop will not be negative.
+	 */
+	if (!found) {
+		for (i = 0; i < ppmu->n_counter; ++i) {
+			if (is_limited_pmc(i + 1))
+				continue;
+			val = read_pmc(i + 1);
+			if ((int)val < 0)
+				write_pmc(i + 1, 0);
+		}
+	}
+
+	/*
+	 * Reset MMCR0 to its normal value.  This will set PMXE and
+	 * clear FC (freeze counters) and PMAO (perf mon alert occurred)
+	 * and thus allow interrupts to occur again.
+	 * XXX might want to use MSR.PM to keep the counters frozen until
+	 * we get back out of this interrupt.
+	 */
+	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+
+	if (nmi)
+		nmi_exit();
+	else
+		irq_exit();
+}
+
+void hw_perf_counter_setup(int cpu)
+{
+	struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
+
+	memset(cpuhw, 0, sizeof(*cpuhw));
+	cpuhw->mmcr[0] = MMCR0_FC;
+}
+
+int register_power_pmu(struct power_pmu *pmu)
+{
+	if (ppmu)
+		return -EBUSY;		/* something's already registered */
+
+	ppmu = pmu;
+	pr_info("%s performance monitor hardware support registered\n",
+		pmu->name);
+
+#ifdef MSR_HV
+	/*
+	 * Use FCHV to ignore kernel events if MSR.HV is set.
+	 */
+	if (mfmsr() & MSR_HV)
+		freeze_counters_kernel = MMCR0_FCHV;
+#endif /* CONFIG_PPC64 */
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
new file mode 100644
index 00000000000..db90b0c5c27
--- /dev/null
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -0,0 +1,615 @@
+/*
+ * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for POWER4
+ */
+#define PM_PMC_SH	12	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_UNIT_SH	8	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_LOWER_SH	6
+#define PM_LOWER_MSK	1
+#define PM_LOWER_MSKS	0x40
+#define PM_BYTE_SH	4	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_PMCSEL_MSK	7
+
+/*
+ * Unit code values
+ */
+#define PM_FPU		1
+#define PM_ISU1		2
+#define PM_IFU		3
+#define PM_IDU0		4
+#define PM_ISU1_ALT	6
+#define PM_ISU2		7
+#define PM_IFU_ALT	8
+#define PM_LSU0		9
+#define PM_LSU1		0xc
+#define PM_GPS		0xf
+
+/*
+ * Bits in MMCR0 for POWER4
+ */
+#define MMCR0_PMC1SEL_SH	8
+#define MMCR0_PMC2SEL_SH	1
+#define MMCR_PMCSEL_MSK		0x1f
+
+/*
+ * Bits in MMCR1 for POWER4
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTC0SEL_SH	61
+#define MMCR1_TTM1SEL_SH	59
+#define MMCR1_TTC1SEL_SH	58
+#define MMCR1_TTM2SEL_SH	56
+#define MMCR1_TTC2SEL_SH	55
+#define MMCR1_TTM3SEL_SH	53
+#define MMCR1_TTC3SEL_SH	52
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	50
+#define MMCR1_TD_CP_DBG1SEL_SH	48
+#define MMCR1_TD_CP_DBG2SEL_SH	46
+#define MMCR1_TD_CP_DBG3SEL_SH	44
+#define MMCR1_DEBUG0SEL_SH	43
+#define MMCR1_DEBUG1SEL_SH	42
+#define MMCR1_DEBUG2SEL_SH	41
+#define MMCR1_DEBUG3SEL_SH	40
+#define MMCR1_PMC1_ADDER_SEL_SH	39
+#define MMCR1_PMC2_ADDER_SEL_SH	38
+#define MMCR1_PMC6_ADDER_SEL_SH	37
+#define MMCR1_PMC5_ADDER_SEL_SH	36
+#define MMCR1_PMC8_ADDER_SEL_SH	35
+#define MMCR1_PMC7_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC3SEL_SH	27
+#define MMCR1_PMC4SEL_SH	22
+#define MMCR1_PMC5SEL_SH	17
+#define MMCR1_PMC6SEL_SH	12
+#define MMCR1_PMC7SEL_SH	7
+#define MMCR1_PMC8SEL_SH	2	/* note bit 0 is in MMCRA for GP */
+
+static short mmcr1_adder_bits[8] = {
+	MMCR1_PMC1_ADDER_SEL_SH,
+	MMCR1_PMC2_ADDER_SEL_SH,
+	MMCR1_PMC3_ADDER_SEL_SH,
+	MMCR1_PMC4_ADDER_SEL_SH,
+	MMCR1_PMC5_ADDER_SEL_SH,
+	MMCR1_PMC6_ADDER_SEL_SH,
+	MMCR1_PMC7_ADDER_SEL_SH,
+	MMCR1_PMC8_ADDER_SEL_SH
+};
+
+/*
+ * Bits in MMCRA
+ */
+#define MMCRA_PMC8SEL0_SH	17	/* PMC8SEL bit 0 for GP */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *        |[  >[  >[   >|||[  >[  ><  ><  ><  ><  ><><><><><><><><>
+ *        | UC1 UC2 UC3 ||| PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
+ * 	  \SMPL	        ||\TTC3SEL
+ * 		        |\TTC_IFU_SEL
+ * 		        \TTM2SEL0
+ *
+ * SMPL - SAMPLE_ENABLE constraint
+ *     56: SAMPLE_ENABLE value 0x0100_0000_0000_0000
+ *
+ * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2
+ *     55: UC1 error 0x0080_0000_0000_0000
+ *     54: FPU events needed 0x0040_0000_0000_0000
+ *     53: ISU1 events needed 0x0020_0000_0000_0000
+ *     52: IDU0|ISU2 events needed 0x0010_0000_0000_0000
+ *
+ * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0
+ *     51: UC2 error 0x0008_0000_0000_0000
+ *     50: FPU events needed 0x0004_0000_0000_0000
+ *     49: IFU events needed 0x0002_0000_0000_0000
+ *     48: LSU0 events needed 0x0001_0000_0000_0000
+ *
+ * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1
+ *     47: UC3 error 0x8000_0000_0000
+ *     46: LSU0 events needed 0x4000_0000_0000
+ *     45: IFU events needed 0x2000_0000_0000
+ *     44: IDU0|ISU2 events needed 0x1000_0000_0000
+ *     43: ISU1 events needed 0x0800_0000_0000
+ *
+ * TTM2SEL0
+ *     42: 0 = IDU0 events needed
+ *     	   1 = ISU2 events needed 0x0400_0000_0000
+ *
+ * TTC_IFU_SEL
+ *     41: 0 = IFU.U events needed
+ *     	   1 = IFU.L events needed 0x0200_0000_0000
+ *
+ * TTC3SEL
+ *     40: 0 = LSU1.U events needed
+ *     	   1 = LSU1.L events needed 0x0100_0000_0000
+ *
+ * PS1
+ *     39: PS1 error 0x0080_0000_0000
+ *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
+ *
+ * PS2
+ *     35: PS2 error 0x0008_0000_0000
+ *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
+ *
+ * B0
+ *     28-31: Byte 0 event source 0xf000_0000
+ *     	   1 = FPU
+ * 	   2 = ISU1
+ * 	   3 = IFU
+ * 	   4 = IDU0
+ * 	   7 = ISU2
+ * 	   9 = LSU0
+ * 	   c = LSU1
+ * 	   f = GPS
+ *
+ * B1, B2, B3
+ *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
+ *
+ * P8
+ *     15: P8 error 0x8000
+ *     14-15: Count of events needing PMC8
+ *
+ * P1..P7
+ *     0-13: Count of events needing PMC1..PMC7
+ *
+ * Note: this doesn't allow events using IFU.U to be combined with events
+ * using IFU.L, though that is feasible (using TTM0 and TTM2).  However
+ * there are no listed events for IFU.L (they are debug events not
+ * verified for performance monitoring) so this shouldn't cause a
+ * problem.
+ */
+
+static struct unitinfo {
+	unsigned long	value, mask;
+	int		unit;
+	int		lowerbit;
+} p4_unitinfo[16] = {
+	[PM_FPU]  = { 0x44000000000000ul, 0x88000000000000ul, PM_FPU, 0 },
+	[PM_ISU1] = { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
+	[PM_ISU1_ALT] =
+		    { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
+	[PM_IFU]  = { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
+	[PM_IFU_ALT] =
+		    { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
+	[PM_IDU0] = { 0x10100000000000ul, 0x80840000000000ul, PM_IDU0, 1 },
+	[PM_ISU2] = { 0x10140000000000ul, 0x80840000000000ul, PM_ISU2, 0 },
+	[PM_LSU0] = { 0x01400000000000ul, 0x08800000000000ul, PM_LSU0, 0 },
+	[PM_LSU1] = { 0x00000000000000ul, 0x00010000000000ul, PM_LSU1, 40 },
+	[PM_GPS]  = { 0x00000000000000ul, 0x00000000000000ul, PM_GPS, 0 }
+};
+
+static unsigned char direct_marked_event[8] = {
+	(1<<2) | (1<<3),	/* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
+	(1<<3) | (1<<5),	/* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
+	(1<<3),			/* PMC3: PM_MRK_ST_CMPL_INT */
+	(1<<4) | (1<<5),	/* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
+	(1<<4) | (1<<5),	/* PMC5: PM_MRK_GRP_TIMEO */
+	(1<<3) | (1<<4) | (1<<5),
+		/* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
+	(1<<4) | (1<<5),	/* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
+	(1<<4),			/* PMC8: PM_MRK_LSU_FIN */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int p4_marked_instr_event(u64 event)
+{
+	int pmc, psel, unit, byte, bit;
+	unsigned int mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc) {
+		if (direct_marked_event[pmc - 1] & (1 << psel))
+			return 1;
+		if (psel == 0)		/* add events */
+			bit = (pmc <= 4)? pmc - 1: 8 - pmc;
+		else if (psel == 6)	/* decode events */
+			bit = 4;
+		else
+			return 0;
+	} else
+		bit = psel;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = 0;
+	switch (unit) {
+	case PM_LSU1:
+		if (event & PM_LOWER_MSKS)
+			mask = 1 << 28;		/* byte 7 bit 4 */
+		else
+			mask = 6 << 24;		/* byte 3 bits 1 and 2 */
+		break;
+	case PM_LSU0:
+		/* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */
+		mask = 0x083dff00;
+	}
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int p4_get_constraint(u64 event, unsigned long *maskp,
+			     unsigned long *valp)
+{
+	int pmc, byte, unit, lower, sh;
+	unsigned long mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 8)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		grp = ((pmc - 1) >> 1) & 1;
+	}
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	if (unit) {
+		lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK;
+
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+
+		if (!p4_unitinfo[unit].unit)
+			return -1;
+		mask  |= p4_unitinfo[unit].mask;
+		value |= p4_unitinfo[unit].value;
+		sh = p4_unitinfo[unit].lowerbit;
+		if (sh > 1)
+			value |= (unsigned long)lower << sh;
+		else if (lower != sh)
+			return -1;
+		unit = p4_unitinfo[unit].unit;
+
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (28 - 4 * byte);
+		value |= (unsigned long)unit << (28 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2/5/6 field */
+		mask  |= 0x8000000000ull;
+		value |= 0x1000000000ull;
+	} else {
+		/* increment PMC3/4/7/8 field */
+		mask  |= 0x800000000ull;
+		value |= 0x100000000ull;
+	}
+
+	/* Marked instruction events need sample_enable set */
+	if (p4_marked_instr_event(event)) {
+		mask  |= 1ull << 56;
+		value |= 1ull << 56;
+	}
+
+	/* PMCSEL=6 decode events on byte 2 need sample_enable clear */
+	if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2)
+		mask  |= 1ull << 56;
+
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static unsigned int ppc_inst_cmpl[] = {
+	0x1001, 0x4001, 0x6001, 0x7001, 0x8001
+};
+
+static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, na;
+
+	alt[0] = event;
+	na = 1;
+
+	/* 2 possibilities for PM_GRP_DISP_REJECT */
+	if (event == 0x8003 || event == 0x0224) {
+		alt[1] = event ^ (0x8003 ^ 0x0224);
+		return 2;
+	}
+
+	/* 2 possibilities for PM_ST_MISS_L1 */
+	if (event == 0x0c13 || event == 0x0c23) {
+		alt[1] = event ^ (0x0c13 ^ 0x0c23);
+		return 2;
+	}
+
+	/* several possibilities for PM_INST_CMPL */
+	for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) {
+		if (event == ppc_inst_cmpl[i]) {
+			for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j)
+				if (j != i)
+					alt[na++] = ppc_inst_cmpl[j];
+			break;
+		}
+	}
+
+	return na;
+}
+
+static int p4_compute_mmcr(u64 event[], int n_ev,
+			   unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned int pmc, unit, byte, psel, lower;
+	unsigned int ttm, grp;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	unsigned int unitlower = 0;
+	int i;
+
+	if (n_ev > 8)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2/5/6 vs 3/4/7/8 use */
+			++pmc_grp_use[((pmc - 1) >> 1) & 1];
+		}
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK;
+		if (unit) {
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (unit == 6 || unit == 8)
+				/* map alt ISU1/IFU codes: 6->2, 8->3 */
+				unit = (unit >> 1) - 1;
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			lower <<= unit;
+			if (unituse[unit] && lower != (unitlower & lower))
+				return -1;
+			unituse[unit] = 1;
+			unitlower |= lower;
+		}
+	}
+	if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2.
+	 * Each TTMx can only select one unit, but since
+	 * units 2 and 6 are both ISU1, and 3 and 8 are both IFU,
+	 * we have some choices.
+	 */
+	if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) {
+		unituse[6] = 1;		/* Move 2 to 6 */
+		unituse[2] = 0;
+	}
+	if (unituse[3] & (unituse[1] | unituse[2])) {
+		unituse[8] = 1;		/* Move 3 to 8 */
+		unituse[3] = 0;
+		unitlower = (unitlower & ~8) | ((unitlower & 8) << 5);
+	}
+	/* Check only one unit per TTMx */
+	if (unituse[1] + unituse[2] + unituse[3] > 1 ||
+	    unituse[4] + unituse[6] + unituse[7] > 1 ||
+	    unituse[8] + unituse[9] > 1 ||
+	    (unituse[5] | unituse[10] | unituse[11] |
+	     unituse[13] | unituse[14]))
+		return -1;
+
+	/* Set TTMxSEL fields.  Note, units 1-3 => TTM0SEL codes 0-2 */
+	mmcr1 |= (unsigned long)(unituse[3] * 2 + unituse[2])
+		<< MMCR1_TTM0SEL_SH;
+	mmcr1 |= (unsigned long)(unituse[7] * 3 + unituse[6] * 2)
+		<< MMCR1_TTM1SEL_SH;
+	mmcr1 |= (unsigned long)unituse[9] << MMCR1_TTM2SEL_SH;
+
+	/* Set TTCxSEL fields. */
+	if (unitlower & 0xe)
+		mmcr1 |= 1ull << MMCR1_TTC0SEL_SH;
+	if (unitlower & 0xf0)
+		mmcr1 |= 1ull << MMCR1_TTC1SEL_SH;
+	if (unitlower & 0xf00)
+		mmcr1 |= 1ull << MMCR1_TTC2SEL_SH;
+	if (unitlower & 0x7000)
+		mmcr1 |= 1ull << MMCR1_TTC3SEL_SH;
+
+	/* Set byte lane select fields. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == 0xf) {
+			/* special case for GPS */
+			mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte);
+		} else {
+			if (!unituse[unit])
+				ttm = unit - 1;		/* 2->1, 3->2 */
+			else
+				ttm = unit >> 2;
+			mmcr1 |= (unsigned long)ttm
+				<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+		}
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or 00xxx direct event (off or cycles) */
+			if (unit)
+				psel |= 0x10 | ((byte & 2) << 2);
+			for (pmc = 0; pmc < 8; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (unit) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 4) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct event */
+			--pmc;
+			if (psel == 0 && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
+			else if (psel == 6 && byte == 3)
+				/* seem to need to set sample_enable here */
+				mmcra |= MMCRA_SAMPLE_ENABLE;
+			psel |= 8;
+		}
+		if (pmc <= 1)
+			mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc);
+		else
+			mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+		if (pmc == 7)	/* PMC8 */
+			mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH;
+		hwc[i] = pmc;
+		if (p4_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+	}
+
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0xfe)
+		mmcr0 |= MMCR0_PMCjCE;
+
+	mmcra |= 0x2000;	/* mark only one IOP per PPC instruction */
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void p4_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	/*
+	 * Setting the PMCxSEL field to 0 disables PMC x.
+	 * (Note that pmc is 0-based here, not 1-based.)
+	 */
+	if (pmc <= 1) {
+		mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc));
+	} else {
+		mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)));
+		if (pmc == 7)
+			mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH);
+	}
+}
+
+static int p4_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 7,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x1001,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x8c10, /* PM_LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c10, /* PM_LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x330,  /* PM_BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x331,  /* PM_BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x8c10,		0x3c10	},
+		[C(OP_WRITE)] = {	0x7c10,		0xc13	},
+		[C(OP_PREFETCH)] = {	0xc35,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0xc34,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x904	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x900	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x330,		0x331	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static struct power_pmu power4_pmu = {
+	.name			= "POWER4/4+",
+	.n_counter		= 8,
+	.max_alternatives	= 5,
+	.add_fields		= 0x0000001100005555ul,
+	.test_adder		= 0x0011083300000000ul,
+	.compute_mmcr		= p4_compute_mmcr,
+	.get_constraint		= p4_get_constraint,
+	.get_alternatives	= p4_get_alternatives,
+	.disable_pmc		= p4_disable_pmc,
+	.n_generic		= ARRAY_SIZE(p4_generic_events),
+	.generic_events		= p4_generic_events,
+	.cache_events		= &power4_cache_events,
+};
+
+static int init_power4_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4"))
+		return -ENODEV;
+
+	return register_power_pmu(&power4_pmu);
+}
+
+arch_initcall(init_power4_pmu);
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
new file mode 100644
index 00000000000..f4adca8e98a
--- /dev/null
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -0,0 +1,688 @@
+/*
+ * Performance counter support for POWER5+/++ (not POWER5) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3)
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_BYTE_SH	12	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	7
+#define PM_GRS_SH	8	/* Storage subsystem mux select */
+#define PM_GRS_MSK	7
+#define PM_BUSEVENT_MSK	0x80	/* Set if event uses event bus */
+#define PM_PMCSEL_MSK	0x7f
+
+/* Values in PM_UNIT field */
+#define PM_FPU		0
+#define PM_ISU0		1
+#define PM_IFU		2
+#define PM_ISU1		3
+#define PM_IDU		4
+#define PM_ISU0_ALT	6
+#define PM_GRS		7
+#define PM_LSU0		8
+#define PM_LSU1		0xc
+#define PM_LASTUNIT	0xc
+
+/*
+ * Bits in MMCR1 for POWER5+
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	60
+#define MMCR1_TTM2SEL_SH	58
+#define MMCR1_TTM3SEL_SH	56
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	54
+#define MMCR1_TD_CP_DBG1SEL_SH	52
+#define MMCR1_TD_CP_DBG2SEL_SH	50
+#define MMCR1_TD_CP_DBG3SEL_SH	48
+#define MMCR1_GRS_L2SEL_SH	46
+#define MMCR1_GRS_L2SEL_MSK	3
+#define MMCR1_GRS_L3SEL_SH	44
+#define MMCR1_GRS_L3SEL_MSK	3
+#define MMCR1_GRS_MCSEL_SH	41
+#define MMCR1_GRS_MCSEL_MSK	7
+#define MMCR1_GRS_FABSEL_SH	39
+#define MMCR1_GRS_FABSEL_MSK	3
+#define MMCR1_PMC1_ADDER_SEL_SH	35
+#define MMCR1_PMC2_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC1SEL_SH	25
+#define MMCR1_PMC2SEL_SH	17
+#define MMCR1_PMC3SEL_SH	9
+#define MMCR1_PMC4SEL_SH	1
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0x7f
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *             [  ><><>< ><> <><>[  >  <  ><  ><  ><  ><><><><><><>
+ *             NC  G0G1G2 G3 T0T1 UC    B0  B1  B2  B3 P6P5P4P3P2P1
+ *
+ * NC - number of counters
+ *     51: NC error 0x0008_0000_0000_0000
+ *     48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
+ *
+ * G0..G3 - GRS mux constraints
+ *     46-47: GRS_L2SEL value
+ *     44-45: GRS_L3SEL value
+ *     41-44: GRS_MCSEL value
+ *     39-40: GRS_FABSEL value
+ *	Note that these match up with their bit positions in MMCR1
+ *
+ * T0 - TTM0 constraint
+ *     36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
+ *     33: UC3 error 0x02_0000_0000
+ *     32: FPU|IFU|ISU1 events needed 0x01_0000_0000
+ *     31: ISU0 events needed 0x01_8000_0000
+ *     30: IDU|GRS events needed 0x00_4000_0000
+ *
+ * B0
+ *     24-27: Byte 0 event source 0x0f00_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
+ *
+ * P6
+ *     11: P6 error 0x800
+ *     10-11: Count of events needing PMC6
+ *
+ * P1..P5
+ *     0-9: Count of events needing PMC1..PMC5
+ */
+
+static const int grsel_shift[8] = {
+	MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
+	MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
+	MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
+};
+
+/* Masks and values for using events from the various units */
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0x3200000000ul, 0x0100000000ul },
+	[PM_ISU0] =  { 0x0200000000ul, 0x0080000000ul },
+	[PM_ISU1] =  { 0x3200000000ul, 0x3100000000ul },
+	[PM_IFU] =   { 0x3200000000ul, 0x2100000000ul },
+	[PM_IDU] =   { 0x0e00000000ul, 0x0040000000ul },
+	[PM_GRS] =   { 0x0e00000000ul, 0x0c40000000ul },
+};
+
+static int power5p_get_constraint(u64 event, unsigned long *maskp,
+				  unsigned long *valp)
+{
+	int pmc, byte, unit, sh;
+	int bit, fmask;
+	unsigned long mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc >= 5 && !(event == 0x500009 || event == 0x600005))
+			return -1;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+		if (unit > PM_LASTUNIT)
+			return -1;
+		if (unit == PM_ISU0_ALT)
+			unit = PM_ISU0;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (byte >= 4) {
+			if (unit != PM_LSU1)
+				return -1;
+			/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
+			++unit;
+			byte &= 3;
+		}
+		if (unit == PM_GRS) {
+			bit = event & 7;
+			fmask = (bit == 6)? 7: 3;
+			sh = grsel_shift[bit];
+			mask |= (unsigned long)fmask << sh;
+			value |= (unsigned long)((event >> PM_GRS_SH) & fmask)
+				<< sh;
+		}
+		/* Set byte lane select field */
+		mask  |= 0xfUL << (24 - 4 * byte);
+		value |= (unsigned long)unit << (24 - 4 * byte);
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000000000000ul;
+		value |= 0x1000000000000ul;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int power5p_limited_pmc_event(u64 event)
+{
+	int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+
+	return pmc == 5 || pmc == 6;
+}
+
+#define MAX_ALT	3	/* at most 3 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x100c0,  0x40001f },			/* PM_GCT_FULL_CYC */
+	{ 0x120e4,  0x400002 },			/* PM_GRP_DISP_REJECT */
+	{ 0x230e2,  0x323087 },			/* PM_BR_PRED_CR */
+	{ 0x230e3,  0x223087, 0x3230a0 },	/* PM_BR_PRED_TA */
+	{ 0x410c7,  0x441084 },			/* PM_THRD_L2MISS_BOTH_CYC */
+	{ 0x800c4,  0xc20e0 },			/* PM_DTLB_MISS */
+	{ 0xc50c6,  0xc60e0 },			/* PM_MRK_DTLB_MISS */
+	{ 0x100005, 0x600005 },			/* PM_RUN_CYC */
+	{ 0x100009, 0x200009 },			/* PM_INST_CMPL */
+	{ 0x200015, 0x300015 },			/* PM_LSU_LMQ_SRQ_EMPTY_CYC */
+	{ 0x300009, 0x400009 },			/* PM_INST_DISP */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(unsigned int event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static const unsigned char bytedecode_alternatives[4][4] = {
+	/* PMC 1 */	{ 0x21, 0x23, 0x25, 0x27 },
+	/* PMC 2 */	{ 0x07, 0x17, 0x0e, 0x1e },
+	/* PMC 3 */	{ 0x20, 0x22, 0x24, 0x26 },
+	/* PMC 4 */	{ 0x07, 0x17, 0x0e, 0x1e }
+};
+
+/*
+ * Some direct events for decodes of event bus byte 3 have alternative
+ * PMCSEL values on other counters.  This returns the alternative
+ * event code for those that do, or -1 otherwise.  This also handles
+ * alternative PCMSEL values for add events.
+ */
+static s64 find_alternative_bdecode(u64 event)
+{
+	int pmc, altpmc, pp, j;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc == 0 || pmc > 4)
+		return -1;
+	altpmc = 5 - pmc;	/* 1 <-> 4, 2 <-> 3 */
+	pp = event & PM_PMCSEL_MSK;
+	for (j = 0; j < 4; ++j) {
+		if (bytedecode_alternatives[pmc - 1][j] == pp) {
+			return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
+				(altpmc << PM_PMC_SH) |
+				bytedecode_alternatives[altpmc - 1][j];
+		}
+	}
+
+	/* new decode alternatives for power5+ */
+	if (pmc == 1 && (pp == 0x0d || pp == 0x0e))
+		return event + (2 << PM_PMC_SH) + (0x2e - 0x0d);
+	if (pmc == 3 && (pp == 0x2e || pp == 0x2f))
+		return event - (2 << PM_PMC_SH) - (0x2e - 0x0d);
+
+	/* alternative add event encodings */
+	if (pp == 0x10 || pp == 0x28)
+		return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) |
+			(altpmc << PM_PMC_SH);
+
+	return -1;
+}
+
+static int power5p_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	int nlim;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	nlim = power5p_limited_pmc_event(event);
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+			nlim += power5p_limited_pmc_event(ae);
+		}
+	} else {
+		ae = find_alternative_bdecode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC
+		 * and PM_INST_CMPL === PM_RUN_INST_CMPL.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs (e.g.
+		 * 0x100005 for PM_RUN_CYC vs. 0xf for PM_CYC).
+		 * Note that even with these additional alternatives
+		 * we never end up with more than 3 alternatives for any event.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0xf:	/* PM_CYC */
+				alt[j++] = 0x600005;	/* PM_RUN_CYC */
+				++nlim;
+				break;
+			case 0x600005:	/* PM_RUN_CYC */
+				alt[j++] = 0xf;
+				break;
+			case 0x100009:	/* PM_INST_CMPL */
+				alt[j++] = 0x500009;	/* PM_RUN_INST_CMPL */
+				++nlim;
+				break;
+			case 0x500009:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 0x100009;	/* PM_INST_CMPL */
+				alt[j++] = 0x200009;
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
+		/* remove the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (!power5p_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
+		/* remove all but the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (power5p_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
+ * Bit 0 is set if it is marked for all PMCs.
+ * The 0x80 bit indicates a byte decode PMCSEL value.
+ */
+static unsigned char direct_event_is_marked[0x28] = {
+	0,	/* 00 */
+	0x1f,	/* 01 PM_IOPS_CMPL */
+	0x2,	/* 02 PM_MRK_GRP_DISP */
+	0xe,	/* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0,	/* 04 */
+	0x1c,	/* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
+	0x80,	/* 06 */
+	0x80,	/* 07 */
+	0, 0, 0,/* 08 - 0a */
+	0x18,	/* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
+	0,	/* 0c */
+	0x80,	/* 0d */
+	0x80,	/* 0e */
+	0,	/* 0f */
+	0,	/* 10 */
+	0x14,	/* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
+	0,	/* 12 */
+	0x10,	/* 13 PM_MRK_GRP_CMPL */
+	0x1f,	/* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x2,	/* 15 PM_MRK_GRP_ISSUED */
+	0x80,	/* 16 */
+	0x80,	/* 17 */
+	0, 0, 0, 0, 0,
+	0x80,	/* 1d */
+	0x80,	/* 1e */
+	0,	/* 1f */
+	0x80,	/* 20 */
+	0x80,	/* 21 */
+	0x80,	/* 22 */
+	0x80,	/* 23 */
+	0x80,	/* 24 */
+	0x80,	/* 25 */
+	0x80,	/* 26 */
+	0x80,	/* 27 */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power5p_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		if (direct_event_is_marked[psel] & (1 << pmc))
+			return 1;
+		if (direct_event_is_marked[psel] & 0x80)
+			bit = 4;
+		else if (psel == 0x08)
+			bit = pmc - 1;
+		else if (psel == 0x10)
+			bit = 4 - pmc;
+		else if (psel == 0x1b && (pmc == 1 || pmc == 3))
+			bit = 4;
+	} else if ((psel & 0x48) == 0x40) {
+		bit = psel & 7;
+	} else if (psel == 0x28) {
+		bit = pmc - 1;
+	} else if (pmc == 3 && (psel == 0x2e || psel == 0x2f)) {
+		bit = 4;
+	}
+
+	if (!(event & PM_BUSEVENT_MSK) || bit == -1)
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit == PM_LSU0) {
+		/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
+		mask = 0x5dff00;
+	} else if (unit == PM_LSU1 && byte >= 4) {
+		byte -= 4;
+		/* byte 5 bits 6-7, byte 6 bits 0,4, byte 7 bits 0-4,6 */
+		mask = 0x5f11c000;
+	} else
+		return 0;
+
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int power5p_compute_mmcr(u64 event[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm;
+	int i, isbus, bit, grsel;
+	unsigned int pmc_inuse = 0;
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	int ttmuse;
+
+	if (n_ev > 6)
+		return -1;
+
+	/* First pass to count resource use */
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+		if (event[i] & PM_BUSEVENT_MSK) {
+			unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+			byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (unit == PM_ISU0_ALT)
+				unit = PM_ISU0;
+			if (byte >= 4) {
+				if (unit != PM_LSU1)
+					return -1;
+				++unit;
+				byte &= 3;
+			}
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU0 can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU0] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
+		unituse[PM_ISU0_ALT] = 1;	/* move ISU to TTM1 */
+		unituse[PM_ISU0] = 0;
+	}
+	/* Set TTM[01]SEL fields. */
+	ttmuse = 0;
+	for (i = PM_FPU; i <= PM_ISU1; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (unsigned long)i << MMCR1_TTM0SEL_SH;
+	}
+	ttmuse = 0;
+	for (; i <= PM_GRS; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (unsigned long)(i & 3) << MMCR1_TTM1SEL_SH;
+	}
+	if (ttmuse > 1)
+		return -1;
+
+	/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
+			/* get ISU0 through TTM1 rather than TTM0 */
+			unit = PM_ISU0_ALT;
+		} else if (unit == PM_LSU1 + 1) {
+			/* select lower word of LSU1 for this byte */
+			mmcr1 |= 1ul << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		ttm = unit >> 2;
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		isbus = event[i] & PM_BUSEVENT_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		} else if (pmc <= 4) {
+			/* Direct event */
+			--pmc;
+			if (isbus && (byte & 2) &&
+			    (psel == 8 || psel == 0x10 || psel == 0x28))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ul << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+		} else {
+			/* Instructions or run cycles on PMC5/6 */
+			--pmc;
+		}
+		if (isbus && unit == PM_GRS) {
+			bit = psel & 7;
+			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
+			mmcr1 |= (unsigned long)grsel << grsel_shift[bit];
+		}
+		if (power5p_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1))
+			/* select alternate byte lane */
+			psel |= 0x10;
+		if (pmc <= 3)
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power5p_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power5p_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0xf,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x100009,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x1c10a8, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c1088, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x230e4,  /* BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x230e5,  /* BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x1c10a8,	0x3c1088	},
+		[C(OP_WRITE)] = {	0x2c10a8,	0xc10c3		},
+		[C(OP_PREFETCH)] = {	0xc70e7,	-1		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0,		0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	0,		0		},
+		[C(OP_PREFETCH)] = {	0xc50c3,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0xc20e4,	0x800c4		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x800c0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x230e4,	0x230e5		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+static struct power_pmu power5p_pmu = {
+	.name			= "POWER5+/++",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x7000000000055ul,
+	.test_adder		= 0x3000040000000ul,
+	.compute_mmcr		= power5p_compute_mmcr,
+	.get_constraint		= power5p_get_constraint,
+	.get_alternatives	= power5p_get_alternatives,
+	.disable_pmc		= power5p_disable_pmc,
+	.limited_pmc_event	= power5p_limited_pmc_event,
+	.flags			= PPMU_LIMITED_PMC5_6,
+	.n_generic		= ARRAY_SIZE(power5p_generic_events),
+	.generic_events		= power5p_generic_events,
+	.cache_events		= &power5p_cache_events,
+};
+
+static int init_power5p_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
+	    && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++"))
+		return -ENODEV;
+
+	return register_power_pmu(&power5p_pmu);
+}
+
+arch_initcall(init_power5p_pmu);
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
new file mode 100644
index 00000000000..29b2c6c0e83
--- /dev/null
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -0,0 +1,627 @@
+/*
+ * Performance counter support for POWER5 (not POWER5++) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for POWER5 (not POWER5++)
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_BYTE_SH	12	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	7
+#define PM_GRS_SH	8	/* Storage subsystem mux select */
+#define PM_GRS_MSK	7
+#define PM_BUSEVENT_MSK	0x80	/* Set if event uses event bus */
+#define PM_PMCSEL_MSK	0x7f
+
+/* Values in PM_UNIT field */
+#define PM_FPU		0
+#define PM_ISU0		1
+#define PM_IFU		2
+#define PM_ISU1		3
+#define PM_IDU		4
+#define PM_ISU0_ALT	6
+#define PM_GRS		7
+#define PM_LSU0		8
+#define PM_LSU1		0xc
+#define PM_LASTUNIT	0xc
+
+/*
+ * Bits in MMCR1 for POWER5
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	60
+#define MMCR1_TTM2SEL_SH	58
+#define MMCR1_TTM3SEL_SH	56
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	54
+#define MMCR1_TD_CP_DBG1SEL_SH	52
+#define MMCR1_TD_CP_DBG2SEL_SH	50
+#define MMCR1_TD_CP_DBG3SEL_SH	48
+#define MMCR1_GRS_L2SEL_SH	46
+#define MMCR1_GRS_L2SEL_MSK	3
+#define MMCR1_GRS_L3SEL_SH	44
+#define MMCR1_GRS_L3SEL_MSK	3
+#define MMCR1_GRS_MCSEL_SH	41
+#define MMCR1_GRS_MCSEL_MSK	7
+#define MMCR1_GRS_FABSEL_SH	39
+#define MMCR1_GRS_FABSEL_MSK	3
+#define MMCR1_PMC1_ADDER_SEL_SH	35
+#define MMCR1_PMC2_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC1SEL_SH	25
+#define MMCR1_PMC2SEL_SH	17
+#define MMCR1_PMC3SEL_SH	9
+#define MMCR1_PMC4SEL_SH	1
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0x7f
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *         <><>[  ><><>< ><> [  >[ >[ ><  ><  ><  ><  ><><><><><><>
+ *         T0T1 NC G0G1G2 G3  UC PS1PS2 B0  B1  B2  B3 P6P5P4P3P2P1
+ *
+ * T0 - TTM0 constraint
+ *     54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000
+ *
+ * NC - number of counters
+ *     51: NC error 0x0008_0000_0000_0000
+ *     48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
+ *
+ * G0..G3 - GRS mux constraints
+ *     46-47: GRS_L2SEL value
+ *     44-45: GRS_L3SEL value
+ *     41-44: GRS_MCSEL value
+ *     39-40: GRS_FABSEL value
+ *	Note that these match up with their bit positions in MMCR1
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
+ *     37: UC3 error 0x20_0000_0000
+ *     36: FPU|IFU|ISU1 events needed 0x10_0000_0000
+ *     35: ISU0 events needed 0x08_0000_0000
+ *     34: IDU|GRS events needed 0x04_0000_0000
+ *
+ * PS1
+ *     33: PS1 error 0x2_0000_0000
+ *     31-32: count of events needing PMC1/2 0x1_8000_0000
+ *
+ * PS2
+ *     30: PS2 error 0x4000_0000
+ *     28-29: count of events needing PMC3/4 0x3000_0000
+ *
+ * B0
+ *     24-27: Byte 0 event source 0x0f00_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
+ *
+ * P1..P6
+ *     0-11: Count of events needing PMC1..PMC6
+ */
+
+static const int grsel_shift[8] = {
+	MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
+	MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
+	MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
+};
+
+/* Masks and values for using events from the various units */
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0xc0002000000000ul, 0x00001000000000ul },
+	[PM_ISU0] =  { 0x00002000000000ul, 0x00000800000000ul },
+	[PM_ISU1] =  { 0xc0002000000000ul, 0xc0001000000000ul },
+	[PM_IFU] =   { 0xc0002000000000ul, 0x80001000000000ul },
+	[PM_IDU] =   { 0x30002000000000ul, 0x00000400000000ul },
+	[PM_GRS] =   { 0x30002000000000ul, 0x30000400000000ul },
+};
+
+static int power5_get_constraint(u64 event, unsigned long *maskp,
+				 unsigned long *valp)
+{
+	int pmc, byte, unit, sh;
+	int bit, fmask;
+	unsigned long mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc <= 4)
+			grp = (pmc - 1) >> 1;
+		else if (event != 0x500009 && event != 0x600005)
+			return -1;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+		if (unit > PM_LASTUNIT)
+			return -1;
+		if (unit == PM_ISU0_ALT)
+			unit = PM_ISU0;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (byte >= 4) {
+			if (unit != PM_LSU1)
+				return -1;
+			/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
+			++unit;
+			byte &= 3;
+		}
+		if (unit == PM_GRS) {
+			bit = event & 7;
+			fmask = (bit == 6)? 7: 3;
+			sh = grsel_shift[bit];
+			mask |= (unsigned long)fmask << sh;
+			value |= (unsigned long)((event >> PM_GRS_SH) & fmask)
+				<< sh;
+		}
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2; bytes 1 and 3 on PMC3/4.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+		/* Set byte lane select field */
+		mask  |= 0xfUL << (24 - 4 * byte);
+		value |= (unsigned long)unit << (24 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2 field */
+		mask  |= 0x200000000ul;
+		value |= 0x080000000ul;
+	} else if (grp == 1) {
+		/* increment PMC3/4 field */
+		mask  |= 0x40000000ul;
+		value |= 0x10000000ul;
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000000000000ul;
+		value |= 0x1000000000000ul;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+#define MAX_ALT	3	/* at most 3 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x120e4,  0x400002 },			/* PM_GRP_DISP_REJECT */
+	{ 0x410c7,  0x441084 },			/* PM_THRD_L2MISS_BOTH_CYC */
+	{ 0x100005, 0x600005 },			/* PM_RUN_CYC */
+	{ 0x100009, 0x200009, 0x500009 },	/* PM_INST_CMPL */
+	{ 0x300009, 0x400009 },			/* PM_INST_DISP */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u64 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static const unsigned char bytedecode_alternatives[4][4] = {
+	/* PMC 1 */	{ 0x21, 0x23, 0x25, 0x27 },
+	/* PMC 2 */	{ 0x07, 0x17, 0x0e, 0x1e },
+	/* PMC 3 */	{ 0x20, 0x22, 0x24, 0x26 },
+	/* PMC 4 */	{ 0x07, 0x17, 0x0e, 0x1e }
+};
+
+/*
+ * Some direct events for decodes of event bus byte 3 have alternative
+ * PMCSEL values on other counters.  This returns the alternative
+ * event code for those that do, or -1 otherwise.
+ */
+static s64 find_alternative_bdecode(u64 event)
+{
+	int pmc, altpmc, pp, j;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc == 0 || pmc > 4)
+		return -1;
+	altpmc = 5 - pmc;	/* 1 <-> 4, 2 <-> 3 */
+	pp = event & PM_PMCSEL_MSK;
+	for (j = 0; j < 4; ++j) {
+		if (bytedecode_alternatives[pmc - 1][j] == pp) {
+			return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
+				(altpmc << PM_PMC_SH) |
+				bytedecode_alternatives[altpmc - 1][j];
+		}
+	}
+	return -1;
+}
+
+static int power5_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+		}
+	} else {
+		ae = find_alternative_bdecode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+	return nalt;
+}
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
+ * Bit 0 is set if it is marked for all PMCs.
+ * The 0x80 bit indicates a byte decode PMCSEL value.
+ */
+static unsigned char direct_event_is_marked[0x28] = {
+	0,	/* 00 */
+	0x1f,	/* 01 PM_IOPS_CMPL */
+	0x2,	/* 02 PM_MRK_GRP_DISP */
+	0xe,	/* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0,	/* 04 */
+	0x1c,	/* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
+	0x80,	/* 06 */
+	0x80,	/* 07 */
+	0, 0, 0,/* 08 - 0a */
+	0x18,	/* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
+	0,	/* 0c */
+	0x80,	/* 0d */
+	0x80,	/* 0e */
+	0,	/* 0f */
+	0,	/* 10 */
+	0x14,	/* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
+	0,	/* 12 */
+	0x10,	/* 13 PM_MRK_GRP_CMPL */
+	0x1f,	/* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x2,	/* 15 PM_MRK_GRP_ISSUED */
+	0x80,	/* 16 */
+	0x80,	/* 17 */
+	0, 0, 0, 0, 0,
+	0x80,	/* 1d */
+	0x80,	/* 1e */
+	0,	/* 1f */
+	0x80,	/* 20 */
+	0x80,	/* 21 */
+	0x80,	/* 22 */
+	0x80,	/* 23 */
+	0x80,	/* 24 */
+	0x80,	/* 25 */
+	0x80,	/* 26 */
+	0x80,	/* 27 */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power5_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		if (direct_event_is_marked[psel] & (1 << pmc))
+			return 1;
+		if (direct_event_is_marked[psel] & 0x80)
+			bit = 4;
+		else if (psel == 0x08)
+			bit = pmc - 1;
+		else if (psel == 0x10)
+			bit = 4 - pmc;
+		else if (psel == 0x1b && (pmc == 1 || pmc == 3))
+			bit = 4;
+	} else if ((psel & 0x58) == 0x40)
+		bit = psel & 7;
+
+	if (!(event & PM_BUSEVENT_MSK))
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit == PM_LSU0) {
+		/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
+		mask = 0x5dff00;
+	} else if (unit == PM_LSU1 && byte >= 4) {
+		byte -= 4;
+		/* byte 4 bits 1,3,5,7, byte 5 bits 6-7, byte 7 bits 0-4,6 */
+		mask = 0x5f00c0aa;
+	} else
+		return 0;
+
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int power5_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm, grp;
+	int i, isbus, bit, grsel;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	int ttmuse;
+
+	if (n_ev > 6)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2 vs 3/4 use */
+			if (pmc <= 4)
+				++pmc_grp_use[(pmc - 1) >> 1];
+		}
+		if (event[i] & PM_BUSEVENT_MSK) {
+			unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+			byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (unit == PM_ISU0_ALT)
+				unit = PM_ISU0;
+			if (byte >= 4) {
+				if (unit != PM_LSU1)
+					return -1;
+				++unit;
+				byte &= 3;
+			}
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+	if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU0 can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU0] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
+		unituse[PM_ISU0_ALT] = 1;	/* move ISU to TTM1 */
+		unituse[PM_ISU0] = 0;
+	}
+	/* Set TTM[01]SEL fields. */
+	ttmuse = 0;
+	for (i = PM_FPU; i <= PM_ISU1; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (unsigned long)i << MMCR1_TTM0SEL_SH;
+	}
+	ttmuse = 0;
+	for (; i <= PM_GRS; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (unsigned long)(i & 3) << MMCR1_TTM1SEL_SH;
+	}
+	if (ttmuse > 1)
+		return -1;
+
+	/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
+			/* get ISU0 through TTM1 rather than TTM0 */
+			unit = PM_ISU0_ALT;
+		} else if (unit == PM_LSU1 + 1) {
+			/* select lower word of LSU1 for this byte */
+			mmcr1 |= 1ul << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		ttm = unit >> 2;
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		isbus = event[i] & PM_BUSEVENT_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (isbus) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 2) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else if (pmc <= 4) {
+			/* Direct event */
+			--pmc;
+			if ((psel == 8 || psel == 0x10) && isbus && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ul << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+		} else {
+			/* Instructions or run cycles on PMC5/6 */
+			--pmc;
+		}
+		if (isbus && unit == PM_GRS) {
+			bit = psel & 7;
+			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
+			mmcr1 |= (unsigned long)grsel << grsel_shift[bit];
+		}
+		if (power5_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if (pmc <= 3)
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power5_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power5_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0xf,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x100009,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4c1090, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c1088, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x230e4,  /* BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x230e5,  /* BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x4c1090,	0x3c1088	},
+		[C(OP_WRITE)] = {	0x3c1090,	0xc10c3		},
+		[C(OP_PREFETCH)] = {	0xc70e7,	0		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0,		0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x3c309b	},
+		[C(OP_WRITE)] = {	0,		0		},
+		[C(OP_PREFETCH)] = {	0xc50c3,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x2c4090,	0x800c4		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x800c0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x230e4,	0x230e5		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+static struct power_pmu power5_pmu = {
+	.name			= "POWER5",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x7000090000555ul,
+	.test_adder		= 0x3000490000000ul,
+	.compute_mmcr		= power5_compute_mmcr,
+	.get_constraint		= power5_get_constraint,
+	.get_alternatives	= power5_get_alternatives,
+	.disable_pmc		= power5_disable_pmc,
+	.n_generic		= ARRAY_SIZE(power5_generic_events),
+	.generic_events		= power5_generic_events,
+	.cache_events		= &power5_cache_events,
+};
+
+static int init_power5_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
+		return -ENODEV;
+
+	return register_power_pmu(&power5_pmu);
+}
+
+arch_initcall(init_power5_pmu);
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
new file mode 100644
index 00000000000..09ae5bf5bda
--- /dev/null
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -0,0 +1,546 @@
+/*
+ * Performance counter support for POWER6 processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for POWER6
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0x7
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* Unit event comes (TTMxSEL encoding) */
+#define PM_UNIT_MSK	0xf
+#define PM_UNIT_MSKS	(PM_UNIT_MSK << PM_UNIT_SH)
+#define PM_LLAV		0x8000	/* Load lookahead match value */
+#define PM_LLA		0x4000	/* Load lookahead match enable */
+#define PM_BYTE_SH	12	/* Byte of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_SUBUNIT_SH	8	/* Subunit event comes from (NEST_SEL enc.) */
+#define PM_SUBUNIT_MSK	7
+#define PM_SUBUNIT_MSKS	(PM_SUBUNIT_MSK << PM_SUBUNIT_SH)
+#define PM_PMCSEL_MSK	0xff	/* PMCxSEL value */
+#define PM_BUSEVENT_MSK	0xf3700
+
+/*
+ * Bits in MMCR1 for POWER6
+ */
+#define MMCR1_TTM0SEL_SH	60
+#define MMCR1_TTMSEL_SH(n)	(MMCR1_TTM0SEL_SH - (n) * 4)
+#define MMCR1_TTMSEL_MSK	0xf
+#define MMCR1_TTMSEL(m, n)	(((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK)
+#define MMCR1_NESTSEL_SH	45
+#define MMCR1_NESTSEL_MSK	0x7
+#define MMCR1_NESTSEL(m)	(((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK)
+#define MMCR1_PMC1_LLA		(1ul << 44)
+#define MMCR1_PMC1_LLA_VALUE	(1ul << 39)
+#define MMCR1_PMC1_ADDR_SEL	(1ul << 35)
+#define MMCR1_PMC1SEL_SH	24
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0xff
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value >> 1.
+ * Bottom 4 bits are a map of which PMCs are interesting,
+ * top 4 bits say what sort of event:
+ *   0 = direct marked event,
+ *   1 = byte decode event,
+ *   4 = add/and event (PMC1 -> bits 0 & 4),
+ *   5 = add/and event (PMC1 -> bits 1 & 5),
+ *   6 = add/and event (PMC1 -> bits 2 & 6),
+ *   7 = add/and event (PMC1 -> bits 3 & 7).
+ */
+static unsigned char direct_event_is_marked[0x60 >> 1] = {
+	0,	/* 00 */
+	0,	/* 02 */
+	0,	/* 04 */
+	0x07,	/* 06 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0x04,	/* 08 PM_MRK_DFU_FIN */
+	0x06,	/* 0a PM_MRK_IFU_FIN, PM_MRK_INST_FIN */
+	0,	/* 0c */
+	0,	/* 0e */
+	0x02,	/* 10 PM_MRK_INST_DISP */
+	0x08,	/* 12 PM_MRK_LSU_DERAT_MISS */
+	0,	/* 14 */
+	0,	/* 16 */
+	0x0c,	/* 18 PM_THRESH_TIMEO, PM_MRK_INST_FIN */
+	0x0f,	/* 1a PM_MRK_INST_DISP, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x01,	/* 1c PM_MRK_INST_ISSUED */
+	0,	/* 1e */
+	0,	/* 20 */
+	0,	/* 22 */
+	0,	/* 24 */
+	0,	/* 26 */
+	0x15,	/* 28 PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L3MISS */
+	0,	/* 2a */
+	0,	/* 2c */
+	0,	/* 2e */
+	0x4f,	/* 30 */
+	0x7f,	/* 32 */
+	0x4f,	/* 34 */
+	0x5f,	/* 36 */
+	0x6f,	/* 38 */
+	0x4f,	/* 3a */
+	0,	/* 3c */
+	0x08,	/* 3e PM_MRK_INST_TIMEO */
+	0x1f,	/* 40 */
+	0x1f,	/* 42 */
+	0x1f,	/* 44 */
+	0x1f,	/* 46 */
+	0x1f,	/* 48 */
+	0x1f,	/* 4a */
+	0x1f,	/* 4c */
+	0x1f,	/* 4e */
+	0,	/* 50 */
+	0x05,	/* 52 PM_MRK_BR_TAKEN, PM_MRK_BR_MPRED */
+	0x1c,	/* 54 PM_MRK_PTEG_FROM_L3MISS, PM_MRK_PTEG_FROM_L2MISS */
+	0x02,	/* 56 PM_MRK_LD_MISS_L1 */
+	0,	/* 58 */
+	0,	/* 5a */
+	0,	/* 5c */
+	0,	/* 5e */
+};
+
+/*
+ * Masks showing for each unit which bits are marked events.
+ * These masks are in LE order, i.e. 0x00000001 is byte 0, bit 0.
+ */
+static u32 marked_bus_events[16] = {
+	0x01000000,	/* direct events set 1: byte 3 bit 0 */
+	0x00010000,	/* direct events set 2: byte 2 bit 0 */
+	0, 0, 0, 0,	/* IDU, IFU, nest: nothing */
+	0x00000088,	/* VMX set 1: byte 0 bits 3, 7 */
+	0x000000c0,	/* VMX set 2: byte 0 bits 4-7 */
+	0x04010000,	/* LSU set 1: byte 2 bit 0, byte 3 bit 2 */
+	0xff010000u,	/* LSU set 2: byte 2 bit 0, all of byte 3 */
+	0,		/* LSU set 3 */
+	0x00000010,	/* VMX set 3: byte 0 bit 4 */
+	0,		/* BFP set 1 */
+	0x00000022,	/* BFP set 2: byte 0 bits 1, 5 */
+	0, 0
+};
+	
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power6_marked_instr_event(u64 event)
+{
+	int pmc, psel, ptype;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = (event & PM_PMCSEL_MSK) >> 1;	/* drop edge/level bit */
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		ptype = direct_event_is_marked[psel];
+		if (pmc == 0 || !(ptype & (1 << (pmc - 1))))
+			return 0;
+		ptype >>= 4;
+		if (ptype == 0)
+			return 1;
+		if (ptype == 1)
+			bit = 0;
+		else
+			bit = ptype ^ (pmc - 1);
+	} else if ((psel & 0x48) == 0x40)
+		bit = psel & 7;
+
+	if (!(event & PM_BUSEVENT_MSK) || bit == -1)
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = marked_bus_events[unit];
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+/*
+ * Assign PMC numbers and compute MMCR1 value for a set of events
+ */
+static int p6_compute_mmcr(u64 event[], int n_ev,
+			   unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
+	int i;
+	unsigned int pmc, ev, b, u, s, psel;
+	unsigned int ttmset = 0;
+	unsigned int pmc_inuse = 0;
+
+	if (n_ev > 6)
+		return -1;
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;	/* collision! */
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+	}
+	for (i = 0; i < n_ev; ++i) {
+		ev = event[i];
+		pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			--pmc;
+		} else {
+			/* can go on any PMC; find a free one */
+			for (pmc = 0; pmc < 4; ++pmc)
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		}
+		hwc[i] = pmc;
+		psel = ev & PM_PMCSEL_MSK;
+		if (ev & PM_BUSEVENT_MSK) {
+			/* this event uses the event bus */
+			b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK;
+			u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK;
+			/* check for conflict on this byte of event bus */
+			if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u)
+				return -1;
+			mmcr1 |= (unsigned long)u << MMCR1_TTMSEL_SH(b);
+			ttmset |= 1 << b;
+			if (u == 5) {
+				/* Nest events have a further mux */
+				s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
+				if ((ttmset & 0x10) &&
+				    MMCR1_NESTSEL(mmcr1) != s)
+					return -1;
+				ttmset |= 0x10;
+				mmcr1 |= (unsigned long)s << MMCR1_NESTSEL_SH;
+			}
+			if (0x30 <= psel && psel <= 0x3d) {
+				/* these need the PMCx_ADDR_SEL bits */
+				if (b >= 2)
+					mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc;
+			}
+			/* bus select values are different for PMC3/4 */
+			if (pmc >= 2 && (psel & 0x90) == 0x80)
+				psel ^= 0x20;
+		}
+		if (ev & PM_LLA) {
+			mmcr1 |= MMCR1_PMC1_LLA >> pmc;
+			if (ev & PM_LLAV)
+				mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc;
+		}
+		if (power6_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if (pmc < 4)
+			mmcr1 |= (unsigned long)psel << MMCR1_PMCSEL_SH(pmc);
+	}
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0xe)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+/*
+ * Layout of constraint bits:
+ *
+ *	0-1	add field: number of uses of PMC1 (max 1)
+ *	2-3, 4-5, 6-7, 8-9, 10-11: ditto for PMC2, 3, 4, 5, 6
+ *	12-15	add field: number of uses of PMC1-4 (max 4)
+ *	16-19	select field: unit on byte 0 of event bus
+ *	20-23, 24-27, 28-31 ditto for bytes 1, 2, 3
+ *	32-34	select field: nest (subunit) event selector
+ */
+static int p6_get_constraint(u64 event, unsigned long *maskp,
+			     unsigned long *valp)
+{
+	int pmc, byte, sh, subunit;
+	unsigned long mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 4 && !(event == 0x500009 || event == 0x600005))
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		sh = byte * 4 + (16 - PM_UNIT_SH);
+		mask |= PM_UNIT_MSKS << sh;
+		value |= (unsigned long)(event & PM_UNIT_MSKS) << sh;
+		if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) {
+			subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
+			mask  |= (unsigned long)PM_SUBUNIT_MSK << 32;
+			value |= (unsigned long)subunit << 32;
+		}
+	}
+	if (pmc <= 4) {
+		mask  |= 0x8000;	/* add field for count of PMC1-4 uses */
+		value |= 0x1000;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int p6_limited_pmc_event(u64 event)
+{
+	int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+
+	return pmc == 5 || pmc == 6;
+}
+
+#define MAX_ALT	4	/* at most 4 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x0130e8, 0x2000f6, 0x3000fc },	/* PM_PTEG_RELOAD_VALID */
+	{ 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */
+	{ 0x080088, 0x200054, 0x3000f0 },	/* PM_ST_MISS_L1 */
+	{ 0x10000a, 0x2000f4, 0x600005 },	/* PM_RUN_CYC */
+	{ 0x10000b, 0x2000f5 },			/* PM_RUN_COUNT */
+	{ 0x10000e, 0x400010 },			/* PM_PURR */
+	{ 0x100010, 0x4000f8 },			/* PM_FLUSH */
+	{ 0x10001a, 0x200010 },			/* PM_MRK_INST_DISP */
+	{ 0x100026, 0x3000f8 },			/* PM_TB_BIT_TRANS */
+	{ 0x100054, 0x2000f0 },			/* PM_ST_FIN */
+	{ 0x100056, 0x2000fc },			/* PM_L1_ICACHE_MISS */
+	{ 0x1000f0, 0x40000a },			/* PM_INST_IMC_MATCH_CMPL */
+	{ 0x1000f8, 0x200008 },			/* PM_GCT_EMPTY_CYC */
+	{ 0x1000fc, 0x400006 },			/* PM_LSU_DERAT_MISS_CYC */
+	{ 0x20000e, 0x400007 },			/* PM_LSU_DERAT_MISS */
+	{ 0x200012, 0x300012 },			/* PM_INST_DISP */
+	{ 0x2000f2, 0x3000f2 },			/* PM_INST_DISP */
+	{ 0x2000f8, 0x300010 },			/* PM_EXT_INT */
+	{ 0x2000fe, 0x300056 },			/* PM_DATA_FROM_L2MISS */
+	{ 0x2d0030, 0x30001a },			/* PM_MRK_FPU_FIN */
+	{ 0x30000a, 0x400018 },			/* PM_MRK_INST_FIN */
+	{ 0x3000f6, 0x40000e },			/* PM_L1_DCACHE_RELOAD_VALID */
+	{ 0x3000fe, 0x400056 },			/* PM_DATA_FROM_L3MISS */
+};
+
+/*
+ * This could be made more efficient with a binary search on
+ * a presorted list, if necessary
+ */
+static int find_alternatives_list(u64 event)
+{
+	int i, j;
+	unsigned int alt;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			return -1;
+		for (j = 0; j < MAX_ALT; ++j) {
+			alt = event_alternatives[i][j];
+			if (!alt || event < alt)
+				break;
+			if (event == alt)
+				return i;
+		}
+	}
+	return -1;
+}
+
+static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nlim;
+	unsigned int psel, pmc;
+	unsigned int nalt = 1;
+	u64 aevent;
+
+	alt[0] = event;
+	nlim = p6_limited_pmc_event(event);
+
+	/* check the alternatives table */
+	i = find_alternatives_list(event);
+	if (i >= 0) {
+		/* copy out alternatives from list */
+		for (j = 0; j < MAX_ALT; ++j) {
+			aevent = event_alternatives[i][j];
+			if (!aevent)
+				break;
+			if (aevent != event)
+				alt[nalt++] = aevent;
+			nlim += p6_limited_pmc_event(aevent);
+		}
+
+	} else {
+		/* Check for alternative ways of computing sum events */
+		/* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */
+		psel = event & (PM_PMCSEL_MSK & ~1);	/* ignore edge bit */
+		pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc && (psel == 0x32 || psel == 0x34))
+			alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) |
+				((5 - pmc) << PM_PMC_SH);
+
+		/* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */
+		if (pmc && (psel == 0x38 || psel == 0x3a))
+			alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) |
+				((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH);
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC,
+		 * PM_INST_CMPL === PM_RUN_INST_CMPL, PM_PURR === PM_RUN_PURR.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs (e.g.
+		 * 0x10000a for PM_RUN_CYC vs. 0x1e for PM_CYC).
+		 * Note that even with these additional alternatives
+		 * we never end up with more than 4 alternatives for any event.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0x1e:	/* PM_CYC */
+				alt[j++] = 0x600005;	/* PM_RUN_CYC */
+				++nlim;
+				break;
+			case 0x10000a:	/* PM_RUN_CYC */
+				alt[j++] = 0x1e;	/* PM_CYC */
+				break;
+			case 2:		/* PM_INST_CMPL */
+				alt[j++] = 0x500009;	/* PM_RUN_INST_CMPL */
+				++nlim;
+				break;
+			case 0x500009:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 2;		/* PM_INST_CMPL */
+				break;
+			case 0x10000e:	/* PM_PURR */
+				alt[j++] = 0x4000f4;	/* PM_RUN_PURR */
+				break;
+			case 0x4000f4:	/* PM_RUN_PURR */
+				alt[j++] = 0x10000e;	/* PM_PURR */
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
+		/* remove the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (!p6_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
+		/* remove all but the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (p6_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+static void p6_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	/* Set PMCxSEL to 0 to disable PMCx */
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power6_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x1e,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 2,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x280030, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x30000c, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x410a0,  /* BR_PRED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x400052, /* BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ * The "DTLB" and "ITLB" events relate to the DERAT and IERAT.
+ */
+static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x80082,	0x80080		},
+		[C(OP_WRITE)] = {	0x80086,	0x80088		},
+		[C(OP_PREFETCH)] = {	0x810a4,	0		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x100056 	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0x4008c,	0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x150730,	0x250532	},
+		[C(OP_WRITE)] = {	0x250432,	0x150432	},
+		[C(OP_PREFETCH)] = {	0x810a6,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x20000e	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x420ce		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x430e6,	0x400052	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+static struct power_pmu power6_pmu = {
+	.name			= "POWER6",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x1555,
+	.test_adder		= 0x3000,
+	.compute_mmcr		= p6_compute_mmcr,
+	.get_constraint		= p6_get_constraint,
+	.get_alternatives	= p6_get_alternatives,
+	.disable_pmc		= p6_disable_pmc,
+	.limited_pmc_event	= p6_limited_pmc_event,
+	.flags			= PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR,
+	.n_generic		= ARRAY_SIZE(power6_generic_events),
+	.generic_events		= power6_generic_events,
+	.cache_events		= &power6_cache_events,
+};
+
+static int init_power6_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
+		return -ENODEV;
+
+	return register_power_pmu(&power6_pmu);
+}
+
+arch_initcall(init_power6_pmu);
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
new file mode 100644
index 00000000000..5d755ef7ac8
--- /dev/null
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -0,0 +1,374 @@
+/*
+ * Performance counter support for POWER7 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for POWER7
+ */
+#define PM_PMC_SH	16	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	12	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_COMBINE_SH	11	/* Combined event bit */
+#define PM_COMBINE_MSK	1
+#define PM_COMBINE_MSKS	0x800
+#define PM_L2SEL_SH	8	/* L2 event select */
+#define PM_L2SEL_MSK	7
+#define PM_PMCSEL_MSK	0xff
+
+/*
+ * Bits in MMCR1 for POWER7
+ */
+#define MMCR1_TTM0SEL_SH	60
+#define MMCR1_TTM1SEL_SH	56
+#define MMCR1_TTM2SEL_SH	52
+#define MMCR1_TTM3SEL_SH	48
+#define MMCR1_TTMSEL_MSK	0xf
+#define MMCR1_L2SEL_SH		45
+#define MMCR1_L2SEL_MSK		7
+#define MMCR1_PMC1_COMBINE_SH	35
+#define MMCR1_PMC2_COMBINE_SH	34
+#define MMCR1_PMC3_COMBINE_SH	33
+#define MMCR1_PMC4_COMBINE_SH	32
+#define MMCR1_PMC1SEL_SH	24
+#define MMCR1_PMC2SEL_SH	16
+#define MMCR1_PMC3SEL_SH	8
+#define MMCR1_PMC4SEL_SH	0
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0xff
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *                                                 [  ><><><><><><>
+ *                                                  NC P6P5P4P3P2P1
+ *
+ * NC - number of counters
+ *     15: NC error 0x8000
+ *     12-14: number of events needing PMC1-4 0x7000
+ *
+ * P6
+ *     11: P6 error 0x800
+ *     10-11: Count of events needing PMC6
+ *
+ * P1..P5
+ *     0-9: Count of events needing PMC1..PMC5
+ */
+
+static int power7_get_constraint(u64 event, unsigned long *maskp,
+				 unsigned long *valp)
+{
+	int pmc, sh;
+	unsigned long mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc >= 5 && !(event == 0x500fa || event == 0x600f4))
+			return -1;
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000;
+		value |= 0x1000;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+#define MAX_ALT	2	/* at most 2 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x200f2, 0x300f2 },		/* PM_INST_DISP */
+	{ 0x200f4, 0x600f4 },		/* PM_RUN_CYC */
+	{ 0x400fa, 0x500fa },		/* PM_RUN_INST_CMPL */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u64 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static s64 find_alternative_decode(u64 event)
+{
+	int pmc, psel;
+
+	/* this only handles the 4x decode events */
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if ((pmc == 2 || pmc == 4) && (psel & ~7) == 0x40)
+		return event - (1 << PM_PMC_SH) + 8;
+	if ((pmc == 1 || pmc == 3) && (psel & ~7) == 0x48)
+		return event + (1 << PM_PMC_SH) - 8;
+	return -1;
+}
+
+static int power7_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+		}
+	} else {
+		ae = find_alternative_decode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC
+		 * and PM_INST_CMPL === PM_RUN_INST_CMPL.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0x1e:	/* PM_CYC */
+				alt[j++] = 0x600f4;	/* PM_RUN_CYC */
+				break;
+			case 0x600f4:	/* PM_RUN_CYC */
+				alt[j++] = 0x1e;
+				break;
+			case 0x2:	/* PM_PPC_CMPL */
+				alt[j++] = 0x500fa;	/* PM_RUN_INST_CMPL */
+				break;
+			case 0x500fa:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 0x2;	/* PM_PPC_CMPL */
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power7_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int unit;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	psel = event & PM_PMCSEL_MSK & ~1;	/* trim off edge/level bit */
+	if (pmc >= 5)
+		return 0;
+
+	switch (psel >> 4) {
+	case 2:
+		return pmc == 2 || pmc == 4;
+	case 3:
+		if (psel == 0x3c)
+			return pmc == 1;
+		if (psel == 0x3e)
+			return pmc != 2;
+		return 1;
+	case 4:
+	case 5:
+		return unit == 0xd;
+	case 6:
+		if (psel == 0x64)
+			return pmc >= 3;
+	case 8:
+		return unit == 0xd;
+	}
+	return 0;
+}
+
+static int power7_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
+	unsigned int pmc, unit, combine, l2sel, psel;
+	unsigned int pmc_inuse = 0;
+	int i;
+
+	/* First pass to count resource use */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+	}
+
+	/* Second pass: assign PMCs, set all MMCR1 fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		combine = (event[i] >> PM_COMBINE_SH) & PM_COMBINE_MSK;
+		l2sel = (event[i] >> PM_L2SEL_SH) & PM_L2SEL_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct or decoded event */
+			--pmc;
+		}
+		if (pmc <= 3) {
+			mmcr1 |= (unsigned long) unit
+				<< (MMCR1_TTM0SEL_SH - 4 * pmc);
+			mmcr1 |= (unsigned long) combine
+				<< (MMCR1_PMC1_COMBINE_SH - pmc);
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+			if (unit == 6)	/* L2 events */
+				mmcr1 |= (unsigned long) l2sel
+					<< MMCR1_L2SEL_SH;
+		}
+		if (power7_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power7_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
+	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
+	[PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880,	/* LD_REF_L1_LSU*/
+	[PERF_COUNT_HW_CACHE_MISSES] = 0x400f0,		/* LD_MISS_L1	*/
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x10068,	/* BRU_FIN	*/
+	[PERF_COUNT_HW_BRANCH_MISSES] = 0x400f6,	/* BR_MPRED	*/
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x400f0,	0xc880	},
+		[C(OP_WRITE)] = {	0,		0x300f0	},
+		[C(OP_PREFETCH)] = {	0xd8b8,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x200fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0x408a,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x6080,		0x6084	},
+		[C(OP_WRITE)] = {	0x6082,		0x6086	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x300fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x400fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x10068,	0x400f6	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static struct power_pmu power7_pmu = {
+	.name			= "POWER7",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT + 1,
+	.add_fields		= 0x1555ul,
+	.test_adder		= 0x3000ul,
+	.compute_mmcr		= power7_compute_mmcr,
+	.get_constraint		= power7_get_constraint,
+	.get_alternatives	= power7_get_alternatives,
+	.disable_pmc		= power7_disable_pmc,
+	.n_generic		= ARRAY_SIZE(power7_generic_events),
+	.generic_events		= power7_generic_events,
+	.cache_events		= &power7_cache_events,
+};
+
+static int init_power7_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
+		return -ENODEV;
+
+	return register_power_pmu(&power7_pmu);
+}
+
+arch_initcall(init_power7_pmu);
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
new file mode 100644
index 00000000000..6637c87fe70
--- /dev/null
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -0,0 +1,499 @@
+/*
+ * Performance counter support for PPC970-family processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/string.h>
+#include <linux/perf_counter.h>
+#include <linux/string.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Bits in event code for PPC970
+ */
+#define PM_PMC_SH	12	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_UNIT_SH	8	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_SPCSEL_SH	6
+#define PM_SPCSEL_MSK	3
+#define PM_BYTE_SH	4	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_PMCSEL_MSK	0xf
+
+/* Values in PM_UNIT field */
+#define PM_NONE		0
+#define PM_FPU		1
+#define PM_VPU		2
+#define PM_ISU		3
+#define PM_IFU		4
+#define PM_IDU		5
+#define PM_STS		6
+#define PM_LSU0		7
+#define PM_LSU1U	8
+#define PM_LSU1L	9
+#define PM_LASTUNIT	9
+
+/*
+ * Bits in MMCR0 for PPC970
+ */
+#define MMCR0_PMC1SEL_SH	8
+#define MMCR0_PMC2SEL_SH	1
+#define MMCR_PMCSEL_MSK		0x1f
+
+/*
+ * Bits in MMCR1 for PPC970
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	59
+#define MMCR1_TTM3SEL_SH	53
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	50
+#define MMCR1_TD_CP_DBG1SEL_SH	48
+#define MMCR1_TD_CP_DBG2SEL_SH	46
+#define MMCR1_TD_CP_DBG3SEL_SH	44
+#define MMCR1_PMC1_ADDER_SEL_SH	39
+#define MMCR1_PMC2_ADDER_SEL_SH	38
+#define MMCR1_PMC6_ADDER_SEL_SH	37
+#define MMCR1_PMC5_ADDER_SEL_SH	36
+#define MMCR1_PMC8_ADDER_SEL_SH	35
+#define MMCR1_PMC7_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC3SEL_SH	27
+#define MMCR1_PMC4SEL_SH	22
+#define MMCR1_PMC5SEL_SH	17
+#define MMCR1_PMC6SEL_SH	12
+#define MMCR1_PMC7SEL_SH	7
+#define MMCR1_PMC8SEL_SH	2
+
+static short mmcr1_adder_bits[8] = {
+	MMCR1_PMC1_ADDER_SEL_SH,
+	MMCR1_PMC2_ADDER_SEL_SH,
+	MMCR1_PMC3_ADDER_SEL_SH,
+	MMCR1_PMC4_ADDER_SEL_SH,
+	MMCR1_PMC5_ADDER_SEL_SH,
+	MMCR1_PMC6_ADDER_SEL_SH,
+	MMCR1_PMC7_ADDER_SEL_SH,
+	MMCR1_PMC8_ADDER_SEL_SH
+};
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *               <><><>[  >[  >[  ><  ><  ><  ><  ><><><><><><><><>
+ *               SPT0T1 UC  PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
+ *
+ * SP - SPCSEL constraint
+ *     48-49: SPCSEL value 0x3_0000_0000_0000
+ *
+ * T0 - TTM0 constraint
+ *     46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS
+ *     43: UC3 error 0x0800_0000_0000
+ *     42: FPU|IFU|VPU events needed 0x0400_0000_0000
+ *     41: ISU events needed 0x0200_0000_0000
+ *     40: IDU|STS events needed 0x0100_0000_0000
+ *
+ * PS1
+ *     39: PS1 error 0x0080_0000_0000
+ *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
+ *
+ * PS2
+ *     35: PS2 error 0x0008_0000_0000
+ *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
+ *
+ * B0
+ *     28-31: Byte 0 event source 0xf000_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
+ *
+ * P1
+ *     15: P1 error 0x8000
+ *     14-15: Count of events needing PMC1
+ *
+ * P2..P8
+ *     0-13: Count of events needing PMC2..PMC8
+ */
+
+static unsigned char direct_marked_event[8] = {
+	(1<<2) | (1<<3),	/* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
+	(1<<3) | (1<<5),	/* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
+	(1<<3) | (1<<5),	/* PMC3: PM_MRK_ST_CMPL_INT, PM_MRK_VMX_FIN */
+	(1<<4) | (1<<5),	/* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
+	(1<<4) | (1<<5),	/* PMC5: PM_GRP_MRK, PM_MRK_GRP_TIMEO */
+	(1<<3) | (1<<4) | (1<<5),
+		/* PMC6: PM_MRK_ST_STS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
+	(1<<4) | (1<<5),	/* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
+	(1<<4)			/* PMC8: PM_MRK_LSU_FIN */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int p970_marked_instr_event(u64 event)
+{
+	int pmc, psel, unit, byte, bit;
+	unsigned int mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc) {
+		if (direct_marked_event[pmc - 1] & (1 << psel))
+			return 1;
+		if (psel == 0)		/* add events */
+			bit = (pmc <= 4)? pmc - 1: 8 - pmc;
+		else if (psel == 7 || psel == 13)	/* decode events */
+			bit = 4;
+		else
+			return 0;
+	} else
+		bit = psel;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = 0;
+	switch (unit) {
+	case PM_VPU:
+		mask = 0x4c;		/* byte 0 bits 2,3,6 */
+	case PM_LSU0:
+		/* byte 2 bits 0,2,3,4,6; all of byte 1 */
+		mask = 0x085dff00;
+	case PM_LSU1L:
+		mask = 0x50 << 24;	/* byte 3 bits 4,6 */
+		break;
+	}
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+/* Masks and values for using events from the various units */
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0xc80000000000ull, 0x040000000000ull },
+	[PM_VPU] =   { 0xc80000000000ull, 0xc40000000000ull },
+	[PM_ISU] =   { 0x080000000000ull, 0x020000000000ull },
+	[PM_IFU] =   { 0xc80000000000ull, 0x840000000000ull },
+	[PM_IDU] =   { 0x380000000000ull, 0x010000000000ull },
+	[PM_STS] =   { 0x380000000000ull, 0x310000000000ull },
+};
+
+static int p970_get_constraint(u64 event, unsigned long *maskp,
+			       unsigned long *valp)
+{
+	int pmc, byte, unit, sh, spcsel;
+	unsigned long mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 8)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		grp = ((pmc - 1) >> 1) & 1;
+	}
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit) {
+		if (unit > PM_LASTUNIT)
+			return -1;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (28 - 4 * byte);
+		value |= (unsigned long)unit << (28 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2/5/6 field */
+		mask  |= 0x8000000000ull;
+		value |= 0x1000000000ull;
+	} else if (grp == 1) {
+		/* increment PMC3/4/7/8 field */
+		mask  |= 0x800000000ull;
+		value |= 0x100000000ull;
+	}
+	spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
+	if (spcsel) {
+		mask  |= 3ull << 48;
+		value |= (unsigned long)spcsel << 48;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	alt[0] = event;
+
+	/* 2 alternatives for LSU empty */
+	if (event == 0x2002 || event == 0x3002) {
+		alt[1] = event ^ 0x1000;
+		return 2;
+	}
+		
+	return 1;
+}
+
+static int p970_compute_mmcr(u64 event[], int n_ev,
+			     unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm, grp;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 };
+	unsigned char ttmuse[2];
+	unsigned char pmcsel[8];
+	int i;
+	int spcsel;
+
+	if (n_ev > 8)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2/5/6 vs 3/4/7/8 use */
+			++pmc_grp_use[((pmc - 1) >> 1) & 1];
+		}
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (unit) {
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+	if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU]))
+		unitmap[PM_ISU] = 2 | 4;	/* move ISU to TTM1 */
+	/* Set TTM[01]SEL fields. */
+	ttmuse[0] = ttmuse[1] = 0;
+	for (i = PM_FPU; i <= PM_STS; ++i) {
+		if (!unituse[i])
+			continue;
+		ttm = unitmap[i];
+		++ttmuse[(ttm >> 2) & 1];
+		mmcr1 |= (unsigned long)(ttm & ~4) << MMCR1_TTM1SEL_SH;
+	}
+	/* Check only one unit per TTMx */
+	if (ttmuse[0] > 1 || ttmuse[1] > 1)
+		return -1;
+
+	/* Set byte lane select fields and TTM3SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit <= PM_STS)
+			ttm = (unitmap[unit] >> 2) & 1;
+		else if (unit == PM_LSU0)
+			ttm = 2;
+		else {
+			ttm = 3;
+			if (unit == PM_LSU1L && byte >= 2)
+				mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	memset(pmcsel, 0x8, sizeof(pmcsel));	/* 8 means don't count */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			if (unit)
+				psel |= 0x10 | ((byte & 2) << 2);
+			else
+				psel |= 8;
+			for (pmc = 0; pmc < 8; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (unit) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 4) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct event */
+			--pmc;
+			if (psel == 0 && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
+		}
+		pmcsel[pmc] = psel;
+		hwc[i] = pmc;
+		spcsel = (event[i] >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
+		mmcr1 |= spcsel;
+		if (p970_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+	}
+	for (pmc = 0; pmc < 2; ++pmc)
+		mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc);
+	for (; pmc < 8; ++pmc)
+		mmcr1 |= (unsigned long)pmcsel[pmc]
+			<< (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0xfe)
+		mmcr0 |= MMCR0_PMCjCE;
+
+	mmcra |= 0x2000;	/* mark only one IOP per PPC instruction */
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void p970_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	int shift, i;
+
+	if (pmc <= 1) {
+		shift = MMCR0_PMC1SEL_SH - 7 * pmc;
+		i = 0;
+	} else {
+		shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2);
+		i = 1;
+	}
+	/*
+	 * Setting the PMCxSEL field to 0x08 disables PMC x.
+	 */
+	mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift);
+}
+
+static int ppc970_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 7,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 1,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x8810, /* PM_LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3810, /* PM_LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x431,  /* PM_BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES] 		= 0x327,  /* PM_GRP_BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x8810,		0x3810	},
+		[C(OP_WRITE)] = {	0x7810,		0x813	},
+		[C(OP_PREFETCH)] = {	0x731,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0x733,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x704	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x700	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x431,		0x327	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static struct power_pmu ppc970_pmu = {
+	.name			= "PPC970/FX/MP",
+	.n_counter		= 8,
+	.max_alternatives	= 2,
+	.add_fields		= 0x001100005555ull,
+	.test_adder		= 0x013300000000ull,
+	.compute_mmcr		= p970_compute_mmcr,
+	.get_constraint		= p970_get_constraint,
+	.get_alternatives	= p970_get_alternatives,
+	.disable_pmc		= p970_disable_pmc,
+	.n_generic		= ARRAY_SIZE(ppc970_generic_events),
+	.generic_events		= ppc970_generic_events,
+	.cache_events		= &ppc970_cache_events,
+};
+
+static int init_ppc970_pmu(void)
+{
+	if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
+	    && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP"))
+		return -ENODEV;
+
+	return register_power_pmu(&ppc970_pmu);
+}
+
+arch_initcall(init_ppc970_pmu);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7b44a33f03c..3e7135bbe40 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 ce01ff2474d..d4405b95bfa 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 2f0e64b5364..a538824616f 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
@@ -1950,8 +1947,47 @@ static void __init fixup_device_tree_maple(void)
 	prom_setprop(isa, name, "ranges",
 			isa_ranges, sizeof(isa_ranges));
 }
+
+#define CPC925_MC_START		0xf8000000
+#define CPC925_MC_LENGTH	0x1000000
+/* The values for memory-controller don't have right number of cells */
+static void __init fixup_device_tree_maple_memory_controller(void)
+{
+	phandle mc;
+	u32 mc_reg[4];
+	char *name = "/hostbridge@f8000000";
+	struct prom_t *_prom = &RELOC(prom);
+	u32 ac, sc;
+
+	mc = call_prom("finddevice", 1, 1, ADDR(name));
+	if (!PHANDLE_VALID(mc))
+		return;
+
+	if (prom_getproplen(mc, "reg") != 8)
+		return;
+
+	prom_getprop(_prom->root, "#address-cells", &ac, sizeof(ac));
+	prom_getprop(_prom->root, "#size-cells", &sc, sizeof(sc));
+	if ((ac != 2) || (sc != 2))
+		return;
+
+	if (prom_getprop(mc, "reg", mc_reg, sizeof(mc_reg)) == PROM_ERROR)
+		return;
+
+	if (mc_reg[0] != CPC925_MC_START || mc_reg[1] != CPC925_MC_LENGTH)
+		return;
+
+	prom_printf("Fixing up bogus hostbridge on Maple...\n");
+
+	mc_reg[0] = 0x0;
+	mc_reg[1] = CPC925_MC_START;
+	mc_reg[2] = 0x0;
+	mc_reg[3] = CPC925_MC_LENGTH;
+	prom_setprop(mc, name, "reg", mc_reg, sizeof(mc_reg));
+}
 #else
 #define fixup_device_tree_maple()
+#define fixup_device_tree_maple_memory_controller()
 #endif
 
 #ifdef CONFIG_PPC_CHRP
@@ -2192,6 +2228,7 @@ static void __init fixup_device_tree_efika(void)
 static void __init fixup_device_tree(void)
 {
 	fixup_device_tree_maple();
+	fixup_device_tree_maple_memory_controller();
 	fixup_device_tree_chrp();
 	fixup_device_tree_pmac();
 	fixup_device_tree_efika();
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 3635be61f89..9fa2c7dcd05 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 8869001ab5d..54e66da8f74 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 9e1ca745d8f..1d154248cf4 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 c410c606955..1f6816003eb 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 48571ac56fb..eae4511ceea 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -52,6 +52,8 @@
 #include <linux/jiffies.h>
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/perf_counter.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -109,7 +111,7 @@ 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,
@@ -524,6 +526,26 @@ void __init iSeries_time_init_early(void)
 }
 #endif /* CONFIG_PPC_ISERIES */
 
+#if defined(CONFIG_PERF_COUNTERS) && defined(CONFIG_PPC32)
+DEFINE_PER_CPU(u8, perf_counter_pending);
+
+void set_perf_counter_pending(void)
+{
+	get_cpu_var(perf_counter_pending) = 1;
+	set_dec(1);
+	put_cpu_var(perf_counter_pending);
+}
+
+#define test_perf_counter_pending()	__get_cpu_var(perf_counter_pending)
+#define clear_perf_counter_pending()	__get_cpu_var(perf_counter_pending) = 0
+
+#else  /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */
+
+#define test_perf_counter_pending()	0
+#define clear_perf_counter_pending()
+
+#endif /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */
+
 /*
  * For iSeries shared processors, we have to let the hypervisor
  * set the hardware decrementer.  We set a virtual decrementer
@@ -550,6 +572,10 @@ void timer_interrupt(struct pt_regs * regs)
 	set_dec(DECREMENTER_MAX);
 
 #ifdef CONFIG_PPC32
+	if (test_perf_counter_pending()) {
+		clear_perf_counter_pending();
+		perf_counter_do_pending();
+	}
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
@@ -843,6 +869,22 @@ 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 +902,7 @@ 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 +1169,15 @@ 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 678fbff0d20..6f0ae1a9bfa 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 49ac3d6e139..ef36cbbc588 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