Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/booke: Fix breakpoint/watchpoint one-shot behavior
  powerpc: Reduce printk from pseries_mach_cpu_die()
  powerpc: Move checks in pseries_mach_cpu_die()
  powerpc: Reset kernel stack on cpu online from cede state
  powerpc: Fix G5 thermal shutdown
  powerpc/pseries: Pass CPPR value to H_XIRR hcall
  powerpc/booke: Fix a couple typos in the advanced ptrace code
  powerpc: Fix SMP build with disabled CPU hotplugging.
  powerpc: Dynamically allocate pacas
  powerpc/perf: e500 support
  powerpc/perf: Build callchain code regardless of hardware event support.
  powerpc/cpm2: Checkpatch cleanup
  powerpc/86xx: Renaming following split of GE Fanuc joint venture
  powerpc/86xx: Convert gef_pic_lock to raw_spinlock
  powerpc/qe: Convert qe_ic_lock to raw_spinlock
  powerpc/82xx: Convert pci_pic_lock to raw_spinlock
  powerpc/85xx: Convert socrates_fpga_pic_lock to raw_spinlock

35 files changed, 1225 insertions, 257 deletions

diff --git a/arch/powerpc/boot/dts/gef_ppc9a.dts b/arch/powerpc/boot/dts/gef_ppc9a.dts
index 977f260d5e6..83f4b79dff8 100644
--- a/arch/powerpc/boot/dts/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/gef_ppc9a.dts
@@ -1,7 +1,7 @@
 /*
- * GE Fanuc PPC9A Device Tree Source
+ * GE PPC9A Device Tree Source
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
diff --git a/arch/powerpc/boot/dts/gef_sbc310.dts b/arch/powerpc/boot/dts/gef_sbc310.dts
index 8e4efff3bda..fc3a331dd39 100644
--- a/arch/powerpc/boot/dts/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/gef_sbc310.dts
@@ -1,7 +1,7 @@
 /*
- * GE Fanuc SBC310 Device Tree Source
+ * GE SBC310 Device Tree Source
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts
index bb7060078fb..c0671cc9812 100644
--- a/arch/powerpc/boot/dts/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/gef_sbc610.dts
@@ -1,7 +1,7 @@
 /*
- * GE Fanuc SBC610 Device Tree Source
+ * GE SBC610 Device Tree Source
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index d8a693109c8..a011603d407 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -14,6 +14,9 @@
 #define _ASM_POWERPC_PACA_H
 #ifdef __KERNEL__
 
+#ifdef CONFIG_PPC64
+
+#include <linux/init.h>
 #include <asm/types.h>
 #include <asm/lppaca.h>
 #include <asm/mmu.h>
@@ -145,8 +148,19 @@ struct paca_struct {
 #endif
 };
 
-extern struct paca_struct paca[];
-extern void initialise_pacas(void);
+extern struct paca_struct *paca;
+extern __initdata struct paca_struct boot_paca;
+extern void initialise_paca(struct paca_struct *new_paca, int cpu);
+
+extern void allocate_pacas(void);
+extern void free_unused_pacas(void);
+
+#else /* CONFIG_PPC64 */
+
+static inline void allocate_pacas(void) { };
+static inline void free_unused_pacas(void) { };
+
+#endif /* CONFIG_PPC64 */
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PACA_H */
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 3288ce3997e..e6d4ce69b12 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -1,110 +1,23 @@
 /*
- * Performance event support - PowerPC-specific definitions.
+ * Performance event support - hardware-specific disambiguation
  *
- * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ * For now this is a compile-time decision, but eventually it should be
+ * runtime.  This would allow multiplatform perf event support for e300 (fsl
+ * embedded perf counters) plus server/classic, and would accommodate
+ * devices other than the core which provide their own performance counters.
+ *
+ * Copyright 2010 Freescale Semiconductor, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-#include <linux/types.h>
-
-#include <asm/hw_irq.h>
-
-#define MAX_HWEVENTS		8
-#define MAX_EVENT_ALTERNATIVES	8
-#define MAX_LIMITED_HWCOUNTERS	2
-
-/*
- * This struct provides the constants and functions needed to
- * describe the PMU on a particular POWER-family CPU.
- */
-struct power_pmu {
-	const char	*name;
-	int		n_counter;
-	int		max_alternatives;
-	unsigned long	add_fields;
-	unsigned long	test_adder;
-	int		(*compute_mmcr)(u64 events[], int n_ev,
-				unsigned int hwc[], unsigned long mmcr[]);
-	int		(*get_constraint)(u64 event_id, unsigned long *mskp,
-				unsigned long *valp);
-	int		(*get_alternatives)(u64 event_id, unsigned int flags,
-				u64 alt[]);
-	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
-	int		(*limited_pmc_event)(u64 event_id);
-	u32		flags;
-	int		n_generic;
-	int		*generic_events;
-	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
-			       [PERF_COUNT_HW_CACHE_OP_MAX]
-			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
-};
-
-/*
- * Values for power_pmu.flags
- */
-#define PPMU_LIMITED_PMC5_6	1	/* PMC5/6 have limited function */
-#define PPMU_ALT_SIPR		2	/* uses alternate posn for SIPR/HV */
-
-/*
- * Values for flags to get_alternatives()
- */
-#define PPMU_LIMITED_PMC_OK	1	/* can put this on a limited PMC */
-#define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
-#define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
-
-extern int register_power_pmu(struct power_pmu *);
 
-struct pt_regs;
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-
-#define PERF_EVENT_INDEX_OFFSET	1
-
-/*
- * Only override the default definitions in include/linux/perf_event.h
- * if we have hardware PMU support.
- */
 #ifdef CONFIG_PPC_PERF_CTRS
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#include <asm/perf_event_server.h>
 #endif
 
-/*
- * The power_pmu.get_constraint function returns a 32/64-bit value and
- * a 32/64-bit mask that express the constraints between this event_id and
- * other events.
- *
- * The value and mask are divided up into (non-overlapping) bitfields
- * of three different types:
- *
- * Select field: this expresses the constraint that some set of bits
- * in MMCR* needs to be set to a specific value for this event_id.  For a
- * select field, the mask contains 1s in every bit of the field, and
- * the value contains a unique value for each possible setting of the
- * MMCR* bits.  The constraint checking code will ensure that two events
- * that set the same field in their masks have the same value in their
- * value dwords.
- *
- * Add field: this expresses the constraint that there can be at most
- * N events in a particular class.  A field of k bits can be used for
- * N <= 2^(k-1) - 1.  The mask has the most significant bit of the field
- * set (and the other bits 0), and the value has only the least significant
- * bit of the field set.  In addition, the 'add_fields' and 'test_adder'
- * in the struct power_pmu for this processor come into play.  The
- * add_fields value contains 1 in the LSB of the field, and the
- * test_adder contains 2^(k-1) - 1 - N in the field.
- *
- * NAND field: this expresses the constraint that you may not have events
- * in all of a set of classes.  (For example, on PPC970, you can't select
- * events from the FPU, ISU and IDU simultaneously, although any two are
- * possible.)  For N classes, the field is N+1 bits wide, and each class
- * is assigned one bit from the least-significant N bits.  The mask has
- * only the most-significant bit set, and the value has only the bit
- * for the event_id's class set.  The test_adder has the least significant
- * bit set in the field.
- *
- * If an event_id is not subject to the constraint expressed by a particular
- * field, then it will have 0 in both the mask and value for that field.
- */
+#ifdef CONFIG_FSL_EMB_PERF_EVENT
+#include <asm/perf_event_fsl_emb.h>
+#endif
diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h
new file mode 100644
index 00000000000..718a9fa94e6
--- /dev/null
+++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h
@@ -0,0 +1,50 @@
+/*
+ * Performance event support - Freescale embedded specific definitions.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <asm/hw_irq.h>
+
+#define MAX_HWEVENTS 4
+
+/* event flags */
+#define FSL_EMB_EVENT_VALID      1
+#define FSL_EMB_EVENT_RESTRICTED 2
+
+/* upper half of event flags is PMLCb */
+#define FSL_EMB_EVENT_THRESHMUL  0x0000070000000000ULL
+#define FSL_EMB_EVENT_THRESH     0x0000003f00000000ULL
+
+struct fsl_emb_pmu {
+	const char	*name;
+	int		n_counter; /* total number of counters */
+
+	/*
+	 * The number of contiguous counters starting at zero that
+	 * can hold restricted events, or zero if there are no
+	 * restricted events.
+	 *
+	 * This isn't a very flexible method of expressing constraints,
+	 * but it's very simple and is adequate for existing chips.
+	 */
+	int		n_restricted;
+
+	/* Returns event flags and PMLCb (FSL_EMB_EVENT_*) */
+	u64		(*xlate_event)(u64 event_id);
+
+	int		n_generic;
+	int		*generic_events;
+	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+			       [PERF_COUNT_HW_CACHE_OP_MAX]
+			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+int register_fsl_emb_pmu(struct fsl_emb_pmu *);
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
new file mode 100644
index 00000000000..8f1df1208d2
--- /dev/null
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -0,0 +1,110 @@
+/*
+ * Performance event support - PowerPC classic/server specific definitions.
+ *
+ * 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/types.h>
+#include <asm/hw_irq.h>
+
+#define MAX_HWEVENTS		8
+#define MAX_EVENT_ALTERNATIVES	8
+#define MAX_LIMITED_HWCOUNTERS	2
+
+/*
+ * This struct provides the constants and functions needed to
+ * describe the PMU on a particular POWER-family CPU.
+ */
+struct power_pmu {
+	const char	*name;
+	int		n_counter;
+	int		max_alternatives;
+	unsigned long	add_fields;
+	unsigned long	test_adder;
+	int		(*compute_mmcr)(u64 events[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[]);
+	int		(*get_constraint)(u64 event_id, unsigned long *mskp,
+				unsigned long *valp);
+	int		(*get_alternatives)(u64 event_id, unsigned int flags,
+				u64 alt[]);
+	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
+	int		(*limited_pmc_event)(u64 event_id);
+	u32		flags;
+	int		n_generic;
+	int		*generic_events;
+	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+			       [PERF_COUNT_HW_CACHE_OP_MAX]
+			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+/*
+ * Values for power_pmu.flags
+ */
+#define PPMU_LIMITED_PMC5_6	1	/* PMC5/6 have limited function */
+#define PPMU_ALT_SIPR		2	/* uses alternate posn for SIPR/HV */
+
+/*
+ * Values for flags to get_alternatives()
+ */
+#define PPMU_LIMITED_PMC_OK	1	/* can put this on a limited PMC */
+#define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
+#define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
+
+extern int register_power_pmu(struct power_pmu *);
+
+struct pt_regs;
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+
+#define PERF_EVENT_INDEX_OFFSET	1
+
+/*
+ * Only override the default definitions in include/linux/perf_event.h
+ * if we have hardware PMU support.
+ */
+#ifdef CONFIG_PPC_PERF_CTRS
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#endif
+
+/*
+ * The power_pmu.get_constraint function returns a 32/64-bit value and
+ * a 32/64-bit mask that express the constraints between this event_id and
+ * other events.
+ *
+ * The value and mask are divided up into (non-overlapping) bitfields
+ * of three different types:
+ *
+ * Select field: this expresses the constraint that some set of bits
+ * in MMCR* needs to be set to a specific value for this event_id.  For a
+ * select field, the mask contains 1s in every bit of the field, and
+ * the value contains a unique value for each possible setting of the
+ * MMCR* bits.  The constraint checking code will ensure that two events
+ * that set the same field in their masks have the same value in their
+ * value dwords.
+ *
+ * Add field: this expresses the constraint that there can be at most
+ * N events in a particular class.  A field of k bits can be used for
+ * N <= 2^(k-1) - 1.  The mask has the most significant bit of the field
+ * set (and the other bits 0), and the value has only the least significant
+ * bit of the field set.  In addition, the 'add_fields' and 'test_adder'
+ * in the struct power_pmu for this processor come into play.  The
+ * add_fields value contains 1 in the LSB of the field, and the
+ * test_adder contains 2^(k-1) - 1 - N in the field.
+ *
+ * NAND field: this expresses the constraint that you may not have events
+ * in all of a set of classes.  (For example, on PPC970, you can't select
+ * events from the FPU, ISU and IDU simultaneously, although any two are
+ * possible.)  For N classes, the field is N+1 bits wide, and each class
+ * is assigned one bit from the least-significant N bits.  The mask has
+ * only the most-significant bit set, and the value has only the bit
+ * for the event_id's class set.  The test_adder has the least significant
+ * bit set in the field.
+ *
+ * If an event_id is not subject to the constraint expressed by a particular
+ * field, then it will have 0 in both the mask and value for that field.
+ */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 8808d307fe7..414d434a66d 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -421,8 +421,8 @@
 /* Bit definitions related to the DBCR2. */
 #define DBCR2_DAC1US	0xC0000000	/* Data Addr Cmp 1 Sup/User   */
 #define DBCR2_DAC1ER	0x30000000	/* Data Addr Cmp 1 Eff/Real */
-#define DBCR2_DAC2US	0x00000000	/* Data Addr Cmp 2 Sup/User   */
-#define DBCR2_DAC2ER	0x00000000	/* Data Addr Cmp 2 Eff/Real */
+#define DBCR2_DAC2US	0x0C000000	/* Data Addr Cmp 2 Sup/User   */
+#define DBCR2_DAC2ER	0x03000000	/* Data Addr Cmp 2 Eff/Real */
 #define DBCR2_DAC12M	0x00800000	/* DAC 1-2 range enable */
 #define DBCR2_DAC12MM	0x00400000	/* DAC 1-2 Mask mode*/
 #define DBCR2_DAC12MX	0x00C00000	/* DAC 1-2 range eXclusive */
diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index 0de404dfee8..77bb71cfd99 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -31,7 +31,7 @@
 #define PMLCA_FCM0	0x08000000	/* Freeze when PMM==0 */
 #define PMLCA_CE	0x04000000	/* Condition Enable */
 
-#define PMLCA_EVENT_MASK 0x007f0000	/* Event field */
+#define PMLCA_EVENT_MASK 0x00ff0000	/* Event field */
 #define PMLCA_EVENT_SHIFT	16
 
 #define PMRN_PMLCB0	0x110	/* PM Local Control B0 */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c002b041021..877326320e7 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -98,11 +98,16 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
-obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_event.o perf_callchain.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
+
+obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_event.o
 obj64-$(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-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o
+obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
+
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
 ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2fc82bac3bb..8af4949434b 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1808,7 +1808,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
 		.num_pmcs		= 4,
-		.oprofile_cpu_type	= "ppc/e500", /* xxx - galak, e500mc? */
+		.oprofile_cpu_type	= "ppc/e500mc",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
 		.cpu_setup		= __setup_cpu_e500mc,
 		.machine_check		= machine_check_e500,
diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c
new file mode 100644
index 00000000000..7c07de0d894
--- /dev/null
+++ b/arch/powerpc/kernel/e500-pmu.c
@@ -0,0 +1,129 @@
+/*
+ * Performance counter support for e500 family processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/string.h>
+#include <linux/perf_event.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Map of generic hardware event types to hardware events
+ * Zero if unsupported
+ */
+static int e500_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = 1,
+	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
+	[PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
+	[PERF_COUNT_HW_BRANCH_MISSES] = 15,
+};
+
+#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 e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	/*
+	 * D-cache misses are not split into read/write/prefetch;
+	 * use raw event 41.
+	 */
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	27,		0	},
+		[C(OP_WRITE)] = {	28,		0	},
+		[C(OP_PREFETCH)] = {	29,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	2,		60	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	/*
+	 * Assuming LL means L2, it's not a good match for this model.
+	 * It allocates only on L1 castout or explicit prefetch, and
+	 * does not have separate read/write events (but it does have
+	 * separate instruction/data events).
+	 */
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	/*
+	 * There are data/instruction MMU misses, but that's a miss on
+	 * the chip's internal level-one TLB which is probably not
+	 * what the user wants.  Instead, unified level-two TLB misses
+	 * are reported here.
+	 */
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	26,		66	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	12,		15 	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static int num_events = 128;
+
+/* Upper half of event id is PMLCb, for threshold events */
+static u64 e500_xlate_event(u64 event_id)
+{
+	u32 event_low = (u32)event_id;
+	u64 ret;
+
+	if (event_low >= num_events)
+		return 0;
+
+	ret = FSL_EMB_EVENT_VALID;
+
+	if (event_low >= 76 && event_low <= 81) {
+		ret |= FSL_EMB_EVENT_RESTRICTED;
+		ret |= event_id &
+		       (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH);
+	} else if (event_id &
+	           (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)) {
+		/* Threshold requested on non-threshold event */
+		return 0;
+	}
+
+	return ret;
+}
+
+static struct fsl_emb_pmu e500_pmu = {
+	.name			= "e500 family",
+	.n_counter		= 4,
+	.n_restricted		= 2,
+	.xlate_event		= e500_xlate_event,
+	.n_generic		= ARRAY_SIZE(e500_generic_events),
+	.generic_events		= e500_generic_events,
+	.cache_events		= &e500_cache_events,
+};
+
+static int init_e500_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type)
+		return -ENODEV;
+
+	if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500mc"))
+		num_events = 256;
+	else if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500"))
+		return -ENODEV;
+
+	return register_fsl_emb_pmu(&e500_pmu);
+}
+
+arch_initcall(init_e500_pmu);
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 92580748802..bed9a29ee38 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -219,7 +219,8 @@ generic_secondary_common_init:
 	 * physical cpu id in r24, we need to search the pacas to find
 	 * which logical id maps to our physical one.
 	 */
-	LOAD_REG_ADDR(r13, paca)	/* Get base vaddr of paca array	 */
+	LOAD_REG_ADDR(r13, paca)	/* Load paca pointer		 */
+	ld	r13,0(r13)		/* Get base vaddr of paca array	 */
 	li	r5,0			/* logical cpu id                */
 1:	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
 	cmpw	r6,r24			/* Compare to our id             */
@@ -536,7 +537,8 @@ _GLOBAL(pmac_secondary_start)
 	mtmsrd	r3			/* RI on */
 
 	/* Set up a paca value for this processor. */
-	LOAD_REG_ADDR(r4,paca)		/* Get base vaddr of paca array	*/
+	LOAD_REG_ADDR(r4,paca)		/* Load paca pointer		*/
+	ld	r4,0(r4)		/* Get base vaddr of paca array	*/
 	mulli	r13,r24,PACA_SIZE	/* Calculate vaddr of right paca */
 	add	r13,r13,r4		/* for this processor.		*/
 	mtspr	SPRN_SPRG_PACA,r13	/* Save vaddr of paca in an SPRG*/
@@ -615,6 +617,17 @@ _GLOBAL(start_secondary_prolog)
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
 	bl	.start_secondary
 	b	.
+/*
+ * Reset stack pointer and call start_secondary
+ * to continue with online operation when woken up
+ * from cede in cpu offline.
+ */
+_GLOBAL(start_secondary_resume)
+	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	.start_secondary
+	b	.
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index d16b1ea55d4..0c40c6f476f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -9,11 +9,15 @@
 
 #include <linux/threads.h>
 #include <linux/module.h>
+#include <linux/lmb.h>
 
+#include <asm/firmware.h>
 #include <asm/lppaca.h>
 #include <asm/paca.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
+#include <asm/iseries/lpar_map.h>
+#include <asm/iseries/hv_types.h>
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
@@ -70,37 +74,82 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = {
  * processors.  The processor VPD array needs one entry per physical
  * processor (not thread).
  */
-struct paca_struct paca[NR_CPUS];
+struct paca_struct *paca;
 EXPORT_SYMBOL(paca);
 
-void __init initialise_pacas(void)
-{
-	int cpu;
+struct paca_struct boot_paca;
 
-	/* The TOC register (GPR2) points 32kB into the TOC, so that 64kB
-	 * of the TOC can be addressed using a single machine instruction.
-	 */
+void __init initialise_paca(struct paca_struct *new_paca, int cpu)
+{
+       /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB
+	* of the TOC can be addressed using a single machine instruction.
+	*/
 	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
 
-	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		struct paca_struct *new_paca = &paca[cpu];
-
 #ifdef CONFIG_PPC_BOOK3S
-		new_paca->lppaca_ptr = &lppaca[cpu];
+	new_paca->lppaca_ptr = &lppaca[cpu];
 #else
-		new_paca->kernel_pgd = swapper_pg_dir;
+	new_paca->kernel_pgd = swapper_pg_dir;
 #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->__current = &init_task;
+	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->__current = &init_task;
 #ifdef CONFIG_PPC_STD_MMU_64
-		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
+	new_paca->slb_shadow_ptr = &slb_shadow[cpu];
 #endif /* CONFIG_PPC_STD_MMU_64 */
+}
+
+static int __initdata paca_size;
+
+void __init allocate_pacas(void)
+{
+	int nr_cpus, cpu, limit;
+
+	/*
+	 * We can't take SLB misses on the paca, and we want to access them
+	 * in real mode, so allocate them within the RMA and also within
+	 * the first segment. On iSeries they must be within the area mapped
+	 * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
+	 */
+	limit = min(0x10000000ULL, lmb.rmo_size);
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		limit = min(limit, HvPagesToMap * HVPAGESIZE);
+
+	nr_cpus = NR_CPUS;
+	/* On iSeries we know we can never have more than 64 cpus */
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		nr_cpus = min(64, nr_cpus);
+
+	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus);
+
+	paca = __va(lmb_alloc_base(paca_size, PAGE_SIZE, limit));
+	memset(paca, 0, paca_size);
+
+	printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n",
+		paca_size, nr_cpus, paca);
+
+	/* Can't use for_each_*_cpu, as they aren't functional yet */
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		initialise_paca(&paca[cpu], cpu);
+}
+
+void __init free_unused_pacas(void)
+{
+	int new_size;
+
+	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * num_possible_cpus());
+
+	if (new_size >= paca_size)
+		return;
+
+	lmb_free(__pa(paca) + new_size, paca_size - new_size);
+
+	printk(KERN_DEBUG "Freed %u bytes for unused pacas\n",
+		paca_size - new_size);
 
-	}
+	paca_size = new_size;
 }
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
new file mode 100644
index 00000000000..369872f6cf7
--- /dev/null
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -0,0 +1,654 @@
+/*
+ * Performance event support - Freescale Embedded Performance Monitor
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/reg_fsl_emb.h>
+#include <asm/pmc.h>
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/ptrace.h>
+
+struct cpu_hw_events {
+	int n_events;
+	int disabled;
+	u8  pmcs_enabled;
+	struct perf_event *event[MAX_HWEVENTS];
+};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+static struct fsl_emb_pmu *ppmu;
+
+/* Number of perf_events counting hardware events */
+static atomic_t num_events;
+/* Used to avoid races in calling reserve/release_pmc_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/*
+ * 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)
+{
+#ifdef __powerpc64__
+	return !regs->softe;
+#else
+	return 0;
+#endif
+}
+
+static void perf_event_interrupt(struct pt_regs *regs);
+
+/*
+ * Read one performance monitor counter (PMC).
+ */
+static unsigned long read_pmc(int idx)
+{
+	unsigned long val;
+
+	switch (idx) {
+	case 0:
+		val = mfpmr(PMRN_PMC0);
+		break;
+	case 1:
+		val = mfpmr(PMRN_PMC1);
+		break;
+	case 2:
+		val = mfpmr(PMRN_PMC2);
+		break;
+	case 3:
+		val = mfpmr(PMRN_PMC3);
+		break;
+	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 0:
+		mtpmr(PMRN_PMC0, val);
+		break;
+	case 1:
+		mtpmr(PMRN_PMC1, val);
+		break;
+	case 2:
+		mtpmr(PMRN_PMC2, val);
+		break;
+	case 3:
+		mtpmr(PMRN_PMC3, val);
+		break;
+	default:
+		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
+	}
+
+	isync();
+}
+
+/*
+ * Write one local control A register
+ */
+static void write_pmlca(int idx, unsigned long val)
+{
+	switch (idx) {
+	case 0:
+		mtpmr(PMRN_PMLCA0, val);
+		break;
+	case 1:
+		mtpmr(PMRN_PMLCA1, val);
+		break;
+	case 2:
+		mtpmr(PMRN_PMLCA2, val);
+		break;
+	case 3:
+		mtpmr(PMRN_PMLCA3, val);
+		break;
+	default:
+		printk(KERN_ERR "oops trying to write PMLCA%d\n", idx);
+	}
+
+	isync();
+}
+
+/*
+ * Write one local control B register
+ */
+static void write_pmlcb(int idx, unsigned long val)
+{
+	switch (idx) {
+	case 0:
+		mtpmr(PMRN_PMLCB0, val);
+		break;
+	case 1:
+		mtpmr(PMRN_PMLCB1, val);
+		break;
+	case 2:
+		mtpmr(PMRN_PMLCB2, val);
+		break;
+	case 3:
+		mtpmr(PMRN_PMLCB3, val);
+		break;
+	default:
+		printk(KERN_ERR "oops trying to write PMLCB%d\n", idx);
+	}
+
+	isync();
+}
+
+static void fsl_emb_pmu_read(struct perf_event *event)
+{
+	s64 val, delta, prev;
+
+	/*
+	 * 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(&event->hw.prev_count);
+		barrier();
+		val = read_pmc(event->hw.idx);
+	} while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
+
+	/* The counters are only 32 bits wide */
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &event->count);
+	atomic64_sub(delta, &event->hw.period_left);
+}
+
+/*
+ * Disable all events to prevent PMU interrupts and to allow
+ * events to be added or removed.
+ */
+void hw_perf_disable(void)
+{
+	struct cpu_hw_events *cpuhw;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	if (!cpuhw->disabled) {
+		cpuhw->disabled = 1;
+
+		/*
+		 * Check if we ever enabled the PMU on this cpu.
+		 */
+		if (!cpuhw->pmcs_enabled) {
+			ppc_enable_pmcs();
+			cpuhw->pmcs_enabled = 1;
+		}
+
+		if (atomic_read(&num_events)) {
+			/*
+			 * Set the 'freeze all counters' bit, and disable
+			 * interrupts.  The barrier is to make sure the
+			 * mtpmr has been executed and the PMU has frozen
+			 * the events before we return.
+			 */
+
+			mtpmr(PMRN_PMGC0, PMGC0_FAC);
+			isync();
+		}
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Re-enable all events if disable == 0.
+ * If we were previously disabled and events were added, then
+ * put the new config on the PMU.
+ */
+void hw_perf_enable(void)
+{
+	struct cpu_hw_events *cpuhw;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+	if (!cpuhw->disabled)
+		goto out;
+
+	cpuhw->disabled = 0;
+	ppc_set_pmu_inuse(cpuhw->n_events != 0);
+
+	if (cpuhw->n_events > 0) {
+		mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
+		isync();
+	}
+
+ out:
+	local_irq_restore(flags);
+}
+
+static int collect_events(struct perf_event *group, int max_count,
+			  struct perf_event *ctrs[])
+{
+	int n = 0;
+	struct perf_event *event;
+
+	if (!is_software_event(group)) {
+		if (n >= max_count)
+			return -1;
+		ctrs[n] = group;
+		n++;
+	}
+	list_for_each_entry(event, &group->sibling_list, group_entry) {
+		if (!is_software_event(event) &&
+		    event->state != PERF_EVENT_STATE_OFF) {
+			if (n >= max_count)
+				return -1;
+			ctrs[n] = event;
+			n++;
+		}
+	}
+	return n;
+}
+
+/* perf must be disabled, context locked on entry */
+static int fsl_emb_pmu_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw;
+	int ret = -EAGAIN;
+	int num_counters = ppmu->n_counter;
+	u64 val;
+	int i;
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
+		num_counters = ppmu->n_restricted;
+
+	/*
+	 * Allocate counters from top-down, so that restricted-capable
+	 * counters are kept free as long as possible.
+	 */
+	for (i = num_counters - 1; i >= 0; i--) {
+		if (cpuhw->event[i])
+			continue;
+
+		break;
+	}
+
+	if (i < 0)
+		goto out;
+
+	event->hw.idx = i;
+	cpuhw->event[i] = event;
+	++cpuhw->n_events;
+
+	val = 0;
+	if (event->hw.sample_period) {
+		s64 left = atomic64_read(&event->hw.period_left);
+		if (left < 0x80000000L)
+			val = 0x80000000L - left;
+	}
+	atomic64_set(&event->hw.prev_count, val);
+	write_pmc(i, val);
+	perf_event_update_userpage(event);
+
+	write_pmlcb(i, event->hw.config >> 32);
+	write_pmlca(i, event->hw.config_base);
+
+	ret = 0;
+ out:
+	put_cpu_var(cpu_hw_events);
+	return ret;
+}
+
+/* perf must be disabled, context locked on entry */
+static void fsl_emb_pmu_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw;
+	int i = event->hw.idx;
+
+	if (i < 0)
+		goto out;
+
+	fsl_emb_pmu_read(event);
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	WARN_ON(event != cpuhw->event[event->hw.idx]);
+
+	write_pmlca(i, 0);
+	write_pmlcb(i, 0);
+	write_pmc(i, 0);
+
+	cpuhw->event[i] = NULL;
+	event->hw.idx = -1;
+
+	/*
+	 * TODO: if at least one restricted event exists, and we
+	 * just freed up a non-restricted-capable counter, and
+	 * there is a restricted-capable counter occupied by
+	 * a non-restricted event, migrate that event to the
+	 * vacated counter.
+	 */
+
+	cpuhw->n_events--;
+
+ out:
+	put_cpu_var(cpu_hw_events);
+}
+
+/*
+ * Re-enable interrupts on a event after they were throttled
+ * because they were coming too fast.
+ *
+ * Context is locked on entry, but perf is not disabled.
+ */
+static void fsl_emb_pmu_unthrottle(struct perf_event *event)
+{
+	s64 val, left;
+	unsigned long flags;
+
+	if (event->hw.idx < 0 || !event->hw.sample_period)
+		return;
+	local_irq_save(flags);
+	perf_disable();
+	fsl_emb_pmu_read(event);
+	left = event->hw.sample_period;
+	event->hw.last_period = left;
+	val = 0;
+	if (left < 0x80000000L)
+		val = 0x80000000L - left;
+	write_pmc(event->hw.idx, val);
+	atomic64_set(&event->hw.prev_count, val);
+	atomic64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+	perf_enable();
+	local_irq_restore(flags);
+}
+
+static struct pmu fsl_emb_pmu = {
+	.enable		= fsl_emb_pmu_enable,
+	.disable	= fsl_emb_pmu_disable,
+	.read		= fsl_emb_pmu_read,
+	.unthrottle	= fsl_emb_pmu_unthrottle,
+};
+
+/*
+ * Release the PMU if this is the last perf_event.
+ */
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	if (!atomic_add_unless(&num_events, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_events) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+/*
+ * Translate a generic cache event_id config to a raw event_id 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_event_init(struct perf_event *event)
+{
+	u64 ev;
+	struct perf_event *events[MAX_HWEVENTS];
+	int n;
+	int err;
+	int num_restricted;
+	int i;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		ev = event->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(event->attr.config, &ev);
+		if (err)
+			return ERR_PTR(err);
+		break;
+
+	case PERF_TYPE_RAW:
+		ev = event->attr.config;
+		break;
+
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	event->hw.config = ppmu->xlate_event(ev);
+	if (!(event->hw.config & FSL_EMB_EVENT_VALID))
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * If this is in a group, check if it can go on with all the
+	 * other hardware events in the group.  We assume the event
+	 * hasn't been linked into its leader's sibling list at this point.
+	 */
+	n = 0;
+	if (event->group_leader != event) {
+		n = collect_events(event->group_leader,
+		                   ppmu->n_counter - 1, events);
+		if (n < 0)
+			return ERR_PTR(-EINVAL);
+	}
+
+	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
+		num_restricted = 0;
+		for (i = 0; i < n; i++) {
+			if (events[i]->hw.config & FSL_EMB_EVENT_RESTRICTED)
+				num_restricted++;
+		}
+
+		if (num_restricted >= ppmu->n_restricted)
+			return ERR_PTR(-EINVAL);
+	}
+
+	event->hw.idx = -1;
+
+	event->hw.config_base = PMLCA_CE | PMLCA_FCM1 |
+	                        (u32)((ev << 16) & PMLCA_EVENT_MASK);
+
+	if (event->attr.exclude_user)
+		event->hw.config_base |= PMLCA_FCU;
+	if (event->attr.exclude_kernel)
+		event->hw.config_base |= PMLCA_FCS;
+	if (event->attr.exclude_idle)
+		return ERR_PTR(-ENOTSUPP);
+
+	event->hw.last_period = event->hw.sample_period;
+	atomic64_set(&event->hw.period_left, event->hw.last_period);
+
+	/*
+	 * See if we need to reserve the PMU.
+	 * If no events 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_events)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_events) == 0 &&
+		    reserve_pmc_hardware(perf_event_interrupt))
+			err = -EBUSY;
+		else
+			atomic_inc(&num_events);
+		mutex_unlock(&pmc_reserve_mutex);
+
+		mtpmr(PMRN_PMGC0, PMGC0_FAC);
+		isync();
+	}
+	event->destroy = hw_perf_event_destroy;
+
+	if (err)
+		return ERR_PTR(err);
+	return &fsl_emb_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_event *event, unsigned long val,
+			       struct pt_regs *regs, int nmi)
+{
+	u64 period = event->hw.sample_period;
+	s64 prev, delta, left;
+	int record = 0;
+
+	/* we don't have to worry about interrupts here */
+	prev = atomic64_read(&event->hw.prev_count);
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &event->count);
+
+	/*
+	 * See if the total period for this event has expired,
+	 * and update for the next period.
+	 */
+	val = 0;
+	left = atomic64_read(&event->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 = {
+			.period	= event->hw.last_period,
+		};
+
+		if (perf_event_overflow(event, nmi, &data, regs)) {
+			/*
+			 * Interrupts are coming too fast - throttle them
+			 * by setting the event to 0, so it will be
+			 * at least 2^30 cycles until the next interrupt
+			 * (assuming each event counts at most 2 counts
+			 * per cycle).
+			 */
+			val = 0;
+			left = ~0ULL >> 1;
+		}
+	}
+
+	write_pmc(event->hw.idx, val);
+	atomic64_set(&event->hw.prev_count, val);
+	atomic64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+}
+
+static void perf_event_interrupt(struct pt_regs *regs)
+{
+	int i;
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct perf_event *event;
+	unsigned long val;
+	int found = 0;
+	int nmi;
+
+	nmi = perf_intr_is_nmi(regs);
+	if (nmi)
+		nmi_enter();
+	else
+		irq_enter();
+
+	for (i = 0; i < ppmu->n_counter; ++i) {
+		event = cpuhw->event[i];
+
+		val = read_pmc(i);
+		if ((int)val < 0) {
+			if (event) {
+				/* event has overflowed */
+				found = 1;
+				record_and_restart(event, val, regs, nmi);
+			} else {
+				/*
+				 * Disabled counter is negative,
+				 * reset it just in case.
+				 */
+				write_pmc(i, 0);
+			}
+		}
+	}
+
+	/* PMM will keep counters frozen until we return from the interrupt. */
+	mtmsr(mfmsr() | MSR_PMM);
+	mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
+	isync();
+
+	if (nmi)
+		nmi_exit();
+	else
+		irq_exit();
+}
+
+void hw_perf_event_setup(int cpu)
+{
+	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
+
+	memset(cpuhw, 0, sizeof(*cpuhw));
+}
+
+int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
+{
+	if (ppmu)
+		return -EBUSY;		/* something's already registered */
+
+	ppmu = pmu;
+	pr_info("%s performance monitor hardware support registered\n",
+		pmu->name);
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 43238b2054b..05131d634e7 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -43,6 +43,7 @@
 #include <asm/smp.h>
 #include <asm/system.h>
 #include <asm/mmu.h>
+#include <asm/paca.h>
 #include <asm/pgtable.h>
 #include <asm/pci.h>
 #include <asm/iommu.h>
@@ -721,6 +722,8 @@ void __init early_init_devtree(void *params)
 	 * FIXME .. and the initrd too? */
 	move_device_tree();
 
+	allocate_pacas();
+
 	DBG("Scanning CPUs ...\n");
 
 	/* Retreive CPU related informations from the flat tree
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index d9b05866615..ed2cfe17d25 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -940,7 +940,7 @@ static int del_instruction_bp(struct task_struct *child, int slot)
 {
 	switch (slot) {
 	case 1:
-		if (child->thread.iac1 == 0)
+		if ((child->thread.dbcr0 & DBCR0_IAC1) == 0)
 			return -ENOENT;
 
 		if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
@@ -952,7 +952,7 @@ static int del_instruction_bp(struct task_struct *child, int slot)
 		child->thread.dbcr0 &= ~DBCR0_IAC1;
 		break;
 	case 2:
-		if (child->thread.iac2 == 0)
+		if ((child->thread.dbcr0 & DBCR0_IAC2) == 0)
 			return -ENOENT;
 
 		if (dbcr_iac_range(child) & DBCR_IAC12MODE)
@@ -963,7 +963,7 @@ static int del_instruction_bp(struct task_struct *child, int slot)
 		break;
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case 3:
-		if (child->thread.iac3 == 0)
+		if ((child->thread.dbcr0 & DBCR0_IAC3) == 0)
 			return -ENOENT;
 
 		if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
@@ -975,7 +975,7 @@ static int del_instruction_bp(struct task_struct *child, int slot)
 		child->thread.dbcr0 &= ~DBCR0_IAC3;
 		break;
 	case 4:
-		if (child->thread.iac4 == 0)
+		if ((child->thread.dbcr0 & DBCR0_IAC4) == 0)
 			return -ENOENT;
 
 		if (dbcr_iac_range(child) & DBCR_IAC34MODE)
@@ -1054,7 +1054,7 @@ static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
 static int del_dac(struct task_struct *child, int slot)
 {
 	if (slot == 1) {
-		if (child->thread.dac1 == 0)
+		if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
 			return -ENOENT;
 
 		child->thread.dac1 = 0;
@@ -1070,7 +1070,7 @@ static int del_dac(struct task_struct *child, int slot)
 		child->thread.dvc1 = 0;
 #endif
 	} else if (slot == 2) {
-		if (child->thread.dac1 == 0)
+		if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
 			return -ENOENT;
 
 #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 03dd6a24819..48f0a008b20 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -36,6 +36,7 @@
 #include <linux/lmb.h>
 #include <linux/of_platform.h>
 #include <asm/io.h>
+#include <asm/paca.h>
 #include <asm/prom.h>
 #include <asm/processor.h>
 #include <asm/vdso_datapage.h>
@@ -493,6 +494,8 @@ void __init smp_setup_cpu_maps(void)
 	 * here will have to be reworked
 	 */
 	cpu_init_thread_core_maps(nthreads);
+
+	free_unused_pacas();
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6568406b2a3..63547394048 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -144,9 +144,9 @@ early_param("smt-enabled", early_smt_enabled);
 #endif /* CONFIG_SMP */
 
 /* Put the paca pointer into r13 and SPRG_PACA */
-void __init setup_paca(int cpu)
+static void __init setup_paca(struct paca_struct *new_paca)
 {
-	local_paca = &paca[cpu];
+	local_paca = new_paca;
 	mtspr(SPRN_SPRG_PACA, local_paca);
 #ifdef CONFIG_PPC_BOOK3E
 	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
@@ -176,14 +176,12 @@ void __init early_setup(unsigned long dt_ptr)
 {
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Fill in any unititialised pacas */
-	initialise_pacas();
-
 	/* Identify CPU type */
 	identify_cpu(0, mfspr(SPRN_PVR));
 
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
-	setup_paca(0);
+	initialise_paca(&boot_paca, 0);
+	setup_paca(&boot_paca);
 
 	/* Initialize lockdep early or else spinlocks will blow */
 	lockdep_init();
@@ -203,7 +201,7 @@ void __init early_setup(unsigned long dt_ptr)
 	early_init_devtree(__va(dt_ptr));
 
 	/* Now we know the logical id of our boot cpu, setup the paca. */
-	setup_paca(boot_cpuid);
+	setup_paca(&paca[boot_cpuid]);
 
 	/* Fix up paca fields required for the boot cpu */
 	get_paca()->cpu_start = 1;
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 9d962d7c72c..d4a09f8705b 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -24,7 +24,7 @@
 
 #include "pq2.h"
 
-static DEFINE_SPINLOCK(pci_pic_lock);
+static DEFINE_RAW_SPINLOCK(pci_pic_lock);
 
 struct pq2ads_pci_pic {
 	struct device_node *node;
@@ -45,12 +45,12 @@ static void pq2ads_pci_mask_irq(unsigned int virq)
 
 	if (irq != -1) {
 		unsigned long flags;
-		spin_lock_irqsave(&pci_pic_lock, flags);
+		raw_spin_lock_irqsave(&pci_pic_lock, flags);
 
 		setbits32(&priv->regs->mask, 1 << irq);
 		mb();
 
-		spin_unlock_irqrestore(&pci_pic_lock, flags);
+		raw_spin_unlock_irqrestore(&pci_pic_lock, flags);
 	}
 }
 
@@ -62,9 +62,9 @@ static void pq2ads_pci_unmask_irq(unsigned int virq)
 	if (irq != -1) {
 		unsigned long flags;
 
-		spin_lock_irqsave(&pci_pic_lock, flags);
+		raw_spin_lock_irqsave(&pci_pic_lock, flags);
 		clrbits32(&priv->regs->mask, 1 << irq);
-		spin_unlock_irqrestore(&pci_pic_lock, flags);
+		raw_spin_unlock_irqrestore(&pci_pic_lock, flags);
 	}
 }
 
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 42e87f08aa0..d48527ffc42 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -50,7 +50,7 @@ static struct socrates_fpga_irq_info fpga_irqs[SOCRATES_FPGA_NUM_IRQS] = {
 
 #define socrates_fpga_irq_to_hw(virq)    ((unsigned int)irq_map[virq].hwirq)
 
-static DEFINE_SPINLOCK(socrates_fpga_pic_lock);
+static DEFINE_RAW_SPINLOCK(socrates_fpga_pic_lock);
 
 static void __iomem *socrates_fpga_pic_iobase;
 static struct irq_host *socrates_fpga_pic_irq_host;
@@ -80,9 +80,9 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq)
 	if (i == 3)
 		return NO_IRQ;
 
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	cause = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(i));
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 	for (i = SOCRATES_FPGA_NUM_IRQS - 1; i >= 0; i--) {
 		if (cause >> (i + 16))
 			break;
@@ -116,12 +116,12 @@ static void socrates_fpga_pic_ack(unsigned int virq)
 	hwirq = socrates_fpga_irq_to_hw(virq);
 
 	irq_line = fpga_irqs[hwirq].irq_line;
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
 		& SOCRATES_FPGA_IRQ_MASK;
 	mask |= (1 << (hwirq + 16));
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 }
 
 static void socrates_fpga_pic_mask(unsigned int virq)
@@ -134,12 +134,12 @@ static void socrates_fpga_pic_mask(unsigned int virq)
 	hwirq = socrates_fpga_irq_to_hw(virq);
 
 	irq_line = fpga_irqs[hwirq].irq_line;
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
 		& SOCRATES_FPGA_IRQ_MASK;
 	mask &= ~(1 << hwirq);
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 }
 
 static void socrates_fpga_pic_mask_ack(unsigned int virq)
@@ -152,13 +152,13 @@ static void socrates_fpga_pic_mask_ack(unsigned int virq)
 	hwirq = socrates_fpga_irq_to_hw(virq);
 
 	irq_line = fpga_irqs[hwirq].irq_line;
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
 		& SOCRATES_FPGA_IRQ_MASK;
 	mask &= ~(1 << hwirq);
 	mask |= (1 << (hwirq + 16));
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 }
 
 static void socrates_fpga_pic_unmask(unsigned int virq)
@@ -171,12 +171,12 @@ static void socrates_fpga_pic_unmask(unsigned int virq)
 	hwirq = socrates_fpga_irq_to_hw(virq);
 
 	irq_line = fpga_irqs[hwirq].irq_line;
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
 		& SOCRATES_FPGA_IRQ_MASK;
 	mask |= (1 << hwirq);
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 }
 
 static void socrates_fpga_pic_eoi(unsigned int virq)
@@ -189,12 +189,12 @@ static void socrates_fpga_pic_eoi(unsigned int virq)
 	hwirq = socrates_fpga_irq_to_hw(virq);
 
 	irq_line = fpga_irqs[hwirq].irq_line;
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
 		& SOCRATES_FPGA_IRQ_MASK;
 	mask |= (1 << (hwirq + 16));
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 }
 
 static int socrates_fpga_pic_set_type(unsigned int virq,
@@ -220,14 +220,14 @@ static int socrates_fpga_pic_set_type(unsigned int virq,
 	default:
 		return -EINVAL;
 	}
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQCFG);
 	if (polarity)
 		mask |= (1 << hwirq);
 	else
 		mask &= ~(1 << hwirq);
 	socrates_fpga_pic_write(FPGA_PIC_IRQCFG, mask);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 	return 0;
 }
 
@@ -314,14 +314,14 @@ void socrates_fpga_pic_init(struct device_node *pic)
 
 	socrates_fpga_pic_iobase = of_iomap(pic, 0);
 
-	spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
+	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(0),
 			SOCRATES_FPGA_IRQ_MASK << 16);
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(1),
 			SOCRATES_FPGA_IRQ_MASK << 16);
 	socrates_fpga_pic_write(FPGA_PIC_IRQMASK(2),
 			SOCRATES_FPGA_IRQ_MASK << 16);
-	spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags);
 
 	pr_info("FPGA PIC: Setting up Socrates FPGA PIC\n");
 }
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 2bbfd530d6d..fbe9f362142 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -33,32 +33,32 @@ config MPC8610_HPCD
 	  This option enables support for the MPC8610 HPCD board.
 
 config GEF_PPC9A
-	bool "GE Fanuc PPC9A"
+	bool "GE PPC9A"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
-	  This option enables support for GE Fanuc's PPC9A.
+	  This option enables support for the GE PPC9A.
 
 config GEF_SBC310
-	bool "GE Fanuc SBC310"
+	bool "GE SBC310"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
-	  This option enables support for GE Fanuc's SBC310.
+	  This option enables support for the GE SBC310.
 
 config GEF_SBC610
-	bool "GE Fanuc SBC610"
+	bool "GE SBC610"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	select HAS_RAPIDIO
 	help
-	  This option enables support for GE Fanuc's SBC610.
+	  This option enables support for the GE SBC610.
 
 endif
 
diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c
index b2ea8875adb..11f7b2b6f49 100644
--- a/arch/powerpc/platforms/86xx/gef_gpio.c
+++ b/arch/powerpc/platforms/86xx/gef_gpio.c
@@ -1,9 +1,9 @@
 /*
- * Driver for GE Fanuc's FPGA based GPIO pins
+ * Driver for GE FPGA based GPIO
  *
- * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ * Author: Martyn Welch <martyn.welch@ge.com>
  *
- * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * 2008 (c) GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2.  This program is licensed "as is" without any warranty of any
@@ -164,6 +164,6 @@ static int __init gef_gpio_init(void)
 };
 arch_initcall(gef_gpio_init);
 
-MODULE_DESCRIPTION("GE Fanuc I/O FPGA GPIO driver");
-MODULE_AUTHOR("Martyn Welch <martyn.welch@gefanuc.com");
+MODULE_DESCRIPTION("GE I/O FPGA GPIO driver");
+MODULE_AUTHOR("Martyn Welch <martyn.welch@ge.com");
 MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index 0110a8736d3..6df9e2561c0 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -1,9 +1,9 @@
 /*
- * Interrupt handling for GE Fanuc's FPGA based PIC
+ * Interrupt handling for GE FPGA based PIC
  *
- * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ * Author: Martyn Welch <martyn.welch@ge.com>
  *
- * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * 2008 (c) GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2.  This program is licensed "as is" without any warranty of any
@@ -49,7 +49,7 @@
 #define gef_irq_to_hw(virq)    ((unsigned int)irq_map[virq].hwirq)
 
 
-static DEFINE_SPINLOCK(gef_pic_lock);
+static DEFINE_RAW_SPINLOCK(gef_pic_lock);
 
 static void __iomem *gef_pic_irq_reg_base;
 static struct irq_host *gef_pic_irq_host;
@@ -118,11 +118,11 @@ static void gef_pic_mask(unsigned int virq)
 
 	hwirq = gef_irq_to_hw(virq);
 
-	spin_lock_irqsave(&gef_pic_lock, flags);
+	raw_spin_lock_irqsave(&gef_pic_lock, flags);
 	mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0));
 	mask &= ~(1 << hwirq);
 	out_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0), mask);
-	spin_unlock_irqrestore(&gef_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&gef_pic_lock, flags);
 }
 
 static void gef_pic_mask_ack(unsigned int virq)
@@ -141,11 +141,11 @@ static void gef_pic_unmask(unsigned int virq)
 
 	hwirq = gef_irq_to_hw(virq);
 
-	spin_lock_irqsave(&gef_pic_lock, flags);
+	raw_spin_lock_irqsave(&gef_pic_lock, flags);
 	mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0));
 	mask |= (1 << hwirq);
 	out_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0), mask);
-	spin_unlock_irqrestore(&gef_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&gef_pic_lock, flags);
 }
 
 static struct irq_chip gef_pic_chip = {
@@ -199,7 +199,7 @@ void __init gef_pic_init(struct device_node *np)
 	/* Map the devices registers into memory */
 	gef_pic_irq_reg_base = of_iomap(np, 0);
 
-	spin_lock_irqsave(&gef_pic_lock, flags);
+	raw_spin_lock_irqsave(&gef_pic_lock, flags);
 
 	/* Initialise everything as masked. */
 	out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU0_INTR_MASK, 0);
@@ -208,7 +208,7 @@ void __init gef_pic_init(struct device_node *np)
 	out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU0_MCP_MASK, 0);
 	out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU1_MCP_MASK, 0);
 
-	spin_unlock_irqrestore(&gef_pic_lock, flags);
+	raw_spin_unlock_irqrestore(&gef_pic_lock, flags);
 
 	/* Map controller */
 	gef_pic_cascade_irq = irq_of_parse_and_map(np, 0);
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index a792e5d8581..60ce07e3910 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -1,9 +1,9 @@
 /*
- * GE Fanuc PPC9A board support
+ * GE PPC9A board support
  *
- * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ * Author: Martyn Welch <martyn.welch@ge.com>
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -82,7 +82,7 @@ static void __init gef_ppc9a_setup_arch(void)
 	}
 #endif
 
-	printk(KERN_INFO "GE Fanuc Intelligent Platforms PPC9A 6U VME SBC\n");
+	printk(KERN_INFO "GE Intelligent Platforms PPC9A 6U VME SBC\n");
 
 #ifdef CONFIG_SMP
 	mpc86xx_smp_init();
@@ -151,7 +151,7 @@ static void gef_ppc9a_show_cpuinfo(struct seq_file *m)
 {
 	uint svid = mfspr(SPRN_SVR);
 
-	seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n");
+	seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n");
 
 	seq_printf(m, "Revision\t: %u%c\n", gef_ppc9a_get_pcb_rev(),
 		('A' + gef_ppc9a_get_board_rev()));
@@ -235,7 +235,7 @@ static int __init declare_of_platform_devices(void)
 machine_device_initcall(gef_ppc9a, declare_of_platform_devices);
 
 define_machine(gef_ppc9a) {
-	.name			= "GE Fanuc PPC9A",
+	.name			= "GE PPC9A",
 	.probe			= gef_ppc9a_probe,
 	.setup_arch		= gef_ppc9a_setup_arch,
 	.init_IRQ		= gef_ppc9a_init_irq,
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 6a1a613836c..3ecee25bf3e 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -1,9 +1,9 @@
 /*
- * GE Fanuc SBC310 board support
+ * GE SBC310 board support
  *
- * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ * Author: Martyn Welch <martyn.welch@ge.com>
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -82,7 +82,7 @@ static void __init gef_sbc310_setup_arch(void)
 	}
 #endif
 
-	printk(KERN_INFO "GE Fanuc Intelligent Platforms SBC310 6U VPX SBC\n");
+	printk(KERN_INFO "GE Intelligent Platforms SBC310 6U VPX SBC\n");
 
 #ifdef CONFIG_SMP
 	mpc86xx_smp_init();
@@ -142,7 +142,7 @@ static void gef_sbc310_show_cpuinfo(struct seq_file *m)
 {
 	uint svid = mfspr(SPRN_SVR);
 
-	seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n");
+	seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n");
 
 	seq_printf(m, "Board ID\t: 0x%2.2x\n", gef_sbc310_get_board_id());
 	seq_printf(m, "Revision\t: %u%c\n", gef_sbc310_get_pcb_rev(),
@@ -223,7 +223,7 @@ static int __init declare_of_platform_devices(void)
 machine_device_initcall(gef_sbc310, declare_of_platform_devices);
 
 define_machine(gef_sbc310) {
-	.name			= "GE Fanuc SBC310",
+	.name			= "GE SBC310",
 	.probe			= gef_sbc310_probe,
 	.setup_arch		= gef_sbc310_setup_arch,
 	.init_IRQ		= gef_sbc310_init_irq,
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index e10688a0fc4..5090d608d9e 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -1,9 +1,9 @@
 /*
- * GE Fanuc SBC610 board support
+ * GE SBC610 board support
  *
- * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ * Author: Martyn Welch <martyn.welch@ge.com>
  *
- * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -82,7 +82,7 @@ static void __init gef_sbc610_setup_arch(void)
 	}
 #endif
 
-	printk(KERN_INFO "GE Fanuc Intelligent Platforms SBC610 6U VPX SBC\n");
+	printk(KERN_INFO "GE Intelligent Platforms SBC610 6U VPX SBC\n");
 
 #ifdef CONFIG_SMP
 	mpc86xx_smp_init();
@@ -133,7 +133,7 @@ static void gef_sbc610_show_cpuinfo(struct seq_file *m)
 {
 	uint svid = mfspr(SPRN_SVR);
 
-	seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n");
+	seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n");
 
 	seq_printf(m, "Revision\t: %u%c\n", gef_sbc610_get_pcb_rev(),
 		('A' + gef_sbc610_get_board_rev() - 1));
@@ -212,7 +212,7 @@ static int __init declare_of_platform_devices(void)
 machine_device_initcall(gef_sbc610, declare_of_platform_devices);
 
 define_machine(gef_sbc610) {
-	.name			= "GE Fanuc SBC610",
+	.name			= "GE SBC610",
 	.probe			= gef_sbc610_probe,
 	.setup_arch		= gef_sbc610_setup_arch,
 	.init_IRQ		= gef_sbc610_init_irq,
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index fa0f690d386..a8aae0b5457 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -144,6 +144,16 @@ config FSL_EMB_PERFMON
 	  and some e300 cores (c3 and c4).  Select this only if your
 	  core supports the Embedded Performance Monitor APU
 
+config FSL_EMB_PERF_EVENT
+	bool
+	depends on FSL_EMB_PERFMON && PERF_EVENTS && !PPC_PERF_CTRS
+	default y
+
+config FSL_EMB_PERF_EVENT_E500
+	bool
+	depends on FSL_EMB_PERF_EVENT && E500
+	default y
+
 config 4xx
 	bool
 	depends on 40x || 44x
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index 5369653dcf6..fba5bf91507 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -43,17 +43,14 @@ system_reset_iSeries:
 	LOAD_REG_ADDR(r23, alpaca)
 	li	r0,ALPACA_SIZE
 	sub	r23,r13,r23
-	divdu	r23,r23,r0		/* r23 has cpu number */
-	LOAD_REG_ADDR(r13, paca)
-	mulli	r0,r23,PACA_SIZE
-	add	r13,r13,r0
-	mtspr	SPRN_SPRG_PACA,r13	/* Save it away for the future */
-	mfmsr	r24
-	ori	r24,r24,MSR_RI
-	mtmsrd	r24			/* RI on */
-	mr	r24,r23
+	divdu	r24,r23,r0		/* r24 has cpu number */
 	cmpwi	0,r24,0			/* Are we processor 0? */
 	bne	1f
+	LOAD_REG_ADDR(r13, boot_paca)
+	mtspr	SPRN_SPRG_PACA,r13	/* Save it away for the future */
+	mfmsr	r23
+	ori	r23,r23,MSR_RI
+	mtmsrd	r23			/* RI on */
 	b	.__start_initialization_iSeries	/* Start up the first processor */
 1:	mfspr	r4,SPRN_CTRLF
 	li	r5,CTRL_RUNLATCH	/* Turn off the run light */
@@ -86,6 +83,16 @@ system_reset_iSeries:
 #endif
 
 2:
+	/* Load our paca now that it's been allocated */
+	LOAD_REG_ADDR(r13, paca)
+	ld	r13,0(r13)
+	mulli	r0,r24,PACA_SIZE
+	add	r13,r13,r0
+	mtspr	SPRN_SPRG_PACA,r13	/* Save it away for the future */
+	mfmsr	r23
+	ori	r23,r23,MSR_RI
+	mtmsrd	r23			/* RI on */
+
 	HMT_LOW
 #ifdef CONFIG_SMP
 	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index d1b124e44d7..a8e1d5d17a2 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -122,44 +122,32 @@ static void pseries_mach_cpu_die(void)
 		if (!get_lppaca()->shared_proc)
 			get_lppaca()->donate_dedicated_cpu = 1;
 
-		printk(KERN_INFO
-			"cpu %u (hwid %u) ceding for offline with hint %d\n",
-			cpu, hwcpu, cede_latency_hint);
 		while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
 			extended_cede_processor(cede_latency_hint);
-			printk(KERN_INFO "cpu %u (hwid %u) returned from cede.\n",
-				cpu, hwcpu);
-			printk(KERN_INFO
-			"Decrementer value = %x Timebase value = %llx\n",
-			get_dec(), get_tb());
 		}
 
-		printk(KERN_INFO "cpu %u (hwid %u) got prodded to go online\n",
-			cpu, hwcpu);
-
 		if (!get_lppaca()->shared_proc)
 			get_lppaca()->donate_dedicated_cpu = 0;
 		get_lppaca()->idle = 0;
-	}
 
-	if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
-		unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+		if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
+			unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
 
-		/*
-		 * NOTE: Calling start_secondary() here for now to
-		 * start new context.
-		 * However, need to do it cleanly by resetting the
-		 * stack pointer.
-		 */
-		start_secondary();
+			/*
+			 * Call to start_secondary_resume() will not return.
+			 * Kernel stack will be reset and start_secondary()
+			 * will be called to continue the online operation.
+			 */
+			start_secondary_resume();
+		}
+	}
 
-	} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+	/* Requested state is CPU_STATE_OFFLINE at this point */
+	WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE);
 
-		set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
-		unregister_slb_shadow(hard_smp_processor_id(),
-					__pa(get_slb_shadow()));
-		rtas_stop_self();
-	}
+	set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
+	unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+	rtas_stop_self();
 
 	/* Should never get here... */
 	BUG();
diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h
index 22574e0d9d9..75a6f480d93 100644
--- a/arch/powerpc/platforms/pseries/offline_states.h
+++ b/arch/powerpc/platforms/pseries/offline_states.h
@@ -9,10 +9,31 @@ enum cpu_state_vals {
 	CPU_MAX_OFFLINE_STATES
 };
 
+#ifdef CONFIG_HOTPLUG_CPU
 extern enum cpu_state_vals get_cpu_current_state(int cpu);
 extern void set_cpu_current_state(int cpu, enum cpu_state_vals state);
-extern enum cpu_state_vals get_preferred_offline_state(int cpu);
 extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state);
 extern void set_default_offline_state(int cpu);
+#else
+static inline enum cpu_state_vals get_cpu_current_state(int cpu)
+{
+	return CPU_STATE_ONLINE;
+}
+
+static inline void set_cpu_current_state(int cpu, enum cpu_state_vals state)
+{
+}
+
+static inline void set_preferred_offline_state(int cpu, enum cpu_state_vals state)
+{
+}
+
+static inline void set_default_offline_state(int cpu)
+{
+}
+#endif
+
+extern enum cpu_state_vals get_preferred_offline_state(int cpu);
 extern int start_secondary(void);
+extern void start_secondary_resume(void);
 #endif
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index 0603c91538a..a05f8d42785 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -259,12 +259,12 @@ static inline long plpar_ipi(unsigned long servernum, unsigned long mfrr)
 	return plpar_hcall_norets(H_IPI, servernum, mfrr);
 }
 
-static inline long plpar_xirr(unsigned long *xirr_ret)
+static inline long plpar_xirr(unsigned long *xirr_ret, unsigned char cppr)
 {
 	long rc;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 
-	rc = plpar_hcall(H_XIRR, retbuf);
+	rc = plpar_hcall(H_XIRR, retbuf, cppr);
 
 	*xirr_ret = retbuf[0];
 
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 4ca641042ec..1bcedd8b461 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -120,12 +120,12 @@ static inline void direct_qirr_info(int n_cpu, u8 value)
 
 /* LPAR low level accessors */
 
-static inline unsigned int lpar_xirr_info_get(void)
+static inline unsigned int lpar_xirr_info_get(unsigned char cppr)
 {
 	unsigned long lpar_rc;
 	unsigned long return_value;
 
-	lpar_rc = plpar_xirr(&return_value);
+	lpar_rc = plpar_xirr(&return_value, cppr);
 	if (lpar_rc != H_SUCCESS)
 		panic(" bad return code xirr - rc = %lx\n", lpar_rc);
 	return (unsigned int)return_value;
@@ -331,7 +331,8 @@ static unsigned int xics_get_irq_direct(void)
 
 static unsigned int xics_get_irq_lpar(void)
 {
-	unsigned int xirr = lpar_xirr_info_get();
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	unsigned int xirr = lpar_xirr_info_get(os_cppr->stack[os_cppr->index]);
 	unsigned int vec = xics_xirr_vector(xirr);
 	unsigned int irq;
 
diff --git a/arch/powerpc/sysdev/cpm2_pic.h b/arch/powerpc/sysdev/cpm2_pic.h
index 30e5828a278..2c5f70c2448 100644
--- a/arch/powerpc/sysdev/cpm2_pic.h
+++ b/arch/powerpc/sysdev/cpm2_pic.h
@@ -3,6 +3,6 @@
 
 extern unsigned int cpm2_get_irq(void);
 
-extern void cpm2_pic_init(struct device_node*);
+extern void cpm2_pic_init(struct device_node *);
 
 #endif /* _PPC_KERNEL_CPM2_H */
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index d927da893ec..541ba986364 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -33,7 +33,7 @@
 
 #include "qe_ic.h"
 
-static DEFINE_SPINLOCK(qe_ic_lock);
+static DEFINE_RAW_SPINLOCK(qe_ic_lock);
 
 static struct qe_ic_info qe_ic_info[] = {
 	[1] = {
@@ -201,13 +201,13 @@ static void qe_ic_unmask_irq(unsigned int virq)
 	unsigned long flags;
 	u32 temp;
 
-	spin_lock_irqsave(&qe_ic_lock, flags);
+	raw_spin_lock_irqsave(&qe_ic_lock, flags);
 
 	temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg);
 	qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg,
 		    temp | qe_ic_info[src].mask);
 
-	spin_unlock_irqrestore(&qe_ic_lock, flags);
+	raw_spin_unlock_irqrestore(&qe_ic_lock, flags);
 }
 
 static void qe_ic_mask_irq(unsigned int virq)
@@ -217,7 +217,7 @@ static void qe_ic_mask_irq(unsigned int virq)
 	unsigned long flags;
 	u32 temp;
 
-	spin_lock_irqsave(&qe_ic_lock, flags);
+	raw_spin_lock_irqsave(&qe_ic_lock, flags);
 
 	temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg);
 	qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg,
@@ -233,7 +233,7 @@ static void qe_ic_mask_irq(unsigned int virq)
 	 */
 	mb();
 
-	spin_unlock_irqrestore(&qe_ic_lock, flags);
+	raw_spin_unlock_irqrestore(&qe_ic_lock, flags);
 }
 
 static struct irq_chip qe_ic_irq_chip = {