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

10 files changed, 893 insertions, 39 deletions

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;