8 files changed, 120 insertions, 130 deletions

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 9f4c9d4f5803..bd100fcf40d0 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -130,43 +130,5 @@ static inline int irqs_disabled_flags(unsigned long flags)
  */
 struct irq_chip;
 
-#ifdef CONFIG_PERF_EVENTS
-
-#ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
-{
-        unsigned long x;
-
-        asm volatile("lbz %0,%1(13)"
-                : "=r" (x)
-                : "i" (offsetof(struct paca_struct, perf_event_pending)));
-        return x;
-}
-
-static inline void set_perf_event_pending(void)
-{
-        asm volatile("stb %0,%1(13)" : :
-                "r" (1),
-                "i" (offsetof(struct paca_struct, perf_event_pending)));
-}
-
-static inline void clear_perf_event_pending(void)
-{
-        asm volatile("stb %0,%1(13)" : :
-                "r" (0),
-                "i" (offsetof(struct paca_struct, perf_event_pending)));
-}
-#endif /* CONFIG_PPC64 */
-
-#else  /* CONFIG_PERF_EVENTS */
-
-static inline unsigned long test_perf_event_pending(void)
-{
-        return 0;
-}
-
-static inline void clear_perf_event_pending(void) {}
-#endif /* CONFIG_PERF_EVENTS */
-
 #endif  /* __KERNEL__ */
 #endif  /* _ASM_POWERPC_HW_IRQ_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 957ceb7059c5..c09138d150d4 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -133,7 +133,6 @@ int main(void)
         DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
         DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
         DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
-        DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_event_pending));
         DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
 #ifdef CONFIG_PPC_MM_SLICES
         DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 59c928564a03..4ff4da2c238b 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -1,7 +1,8 @@
 /*
  * Contains routines needed to support swiotlb for ppc.
  *
- * Copyright (C) 2009 Becky Bruce, Freescale Semiconductor
+ * Copyright (C) 2009-2010 Freescale Semiconductor, Inc.
+ * Author: Becky Bruce
  *
  * 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
@@ -70,7 +71,7 @@ static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
         sd->max_direct_dma_addr = 0;
 
         /* May need to bounce if the device can't address all of DRAM */
-        if (dma_get_mask(dev) < lmb_end_of_DRAM())
+        if ((dma_get_mask(dev) + 1) < lmb_end_of_DRAM())
                 set_dma_ops(dev, &swiotlb_dma_ops);
 
         return NOTIFY_DONE;
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 07109d843787..42e9d908914a 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -556,15 +556,6 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
         TRACE_AND_RESTORE_IRQ(r5);
 
-#ifdef CONFIG_PERF_EVENTS
-        /* check paca->perf_event_pending if we're enabling ints */
-        lbz     r3,PACAPERFPEND(r13)
-        and.    r3,r3,r5
-        beq     27f
-        bl      .perf_event_do_pending
-27:
-#endif /* CONFIG_PERF_EVENTS */
-
         /* extract EE bit and use it to restore paca->hard_enabled */
         ld      r3,_MSR(r1)
         rldicl  r4,r3,49,63             /* r0 = (r3 >> 15) & 1 */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 64f6f2031c22..066bd31551d5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -53,7 +53,6 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
-#include <linux/perf_event.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -145,11 +144,6 @@ notrace void raw_local_irq_restore(unsigned long en)
         }
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
-        if (test_perf_event_pending()) {
-                clear_perf_event_pending();
-                perf_event_do_pending();
-        }
-
         /*
          * if (get_paca()->hard_enabled) return;
          * But again we need to take care that gcc gets hard_enabled directly
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 08460a2e9f41..43b83c35cf54 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -35,6 +35,9 @@ struct cpu_hw_events {
         u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
         unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
         unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
+
+        unsigned int group_flag;
+        int n_txn_start;
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
@@ -718,66 +721,6 @@ static int collect_events(struct perf_event *group, int max_count,
         return n;
 }
 
-static void event_sched_in(struct perf_event *event)
-{
-        event->state = PERF_EVENT_STATE_ACTIVE;
-        event->oncpu = smp_processor_id();
-        event->tstamp_running += event->ctx->time - event->tstamp_stopped;
-        if (is_software_event(event))
-                event->pmu->enable(event);
-}
-
-/*
- * Called to enable a whole group of events.
- * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
- * Assumes the caller has disabled interrupts and has
- * frozen the PMU with hw_perf_save_disable.
- */
-int hw_perf_group_sched_in(struct perf_event *group_leader,
-               struct perf_cpu_context *cpuctx,
-               struct perf_event_context *ctx)
-{
-        struct cpu_hw_events *cpuhw;
-        long i, n, n0;
-        struct perf_event *sub;
-
-        if (!ppmu)
-                return 0;
-        cpuhw = &__get_cpu_var(cpu_hw_events);
-        n0 = cpuhw->n_events;
-        n = collect_events(group_leader, ppmu->n_counter - n0,
-                           &cpuhw->event[n0], &cpuhw->events[n0],
-                           &cpuhw->flags[n0]);
-        if (n < 0)
-                return -EAGAIN;
-        if (check_excludes(cpuhw->event, cpuhw->flags, n0, n))
-                return -EAGAIN;
-        i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n + n0);
-        if (i < 0)
-                return -EAGAIN;
-        cpuhw->n_events = n0 + n;
-        cpuhw->n_added += n;
-
-        /*
-         * OK, this group can go on; update event states etc.,
-         * and enable any software events
-         */
-        for (i = n0; i < n0 + n; ++i)
-                cpuhw->event[i]->hw.config = cpuhw->events[i];
-        cpuctx->active_oncpu += n;
-        n = 1;
-        event_sched_in(group_leader);
-        list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
-                if (sub->state != PERF_EVENT_STATE_OFF) {
-                        event_sched_in(sub);
-                        ++n;
-                }
-        }
-        ctx->nr_active += n;
-
-        return 1;
-}
-
 /*
  * Add a event to the PMU.
  * If all events are not already frozen, then we disable and
@@ -805,12 +748,22 @@ static int power_pmu_enable(struct perf_event *event)
         cpuhw->event[n0] = event;
         cpuhw->events[n0] = event->hw.config;
         cpuhw->flags[n0] = event->hw.event_base;
+
+        /*
+         * If group events scheduling transaction was started,
+         * skip the schedulability test here, it will be peformed
+         * at commit time(->commit_txn) as a whole
+         */
+        if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED)
+                goto nocheck;
+
         if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
                 goto out;
         if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1))
                 goto out;
-
         event->hw.config = cpuhw->events[n0];
+
+nocheck:
         ++cpuhw->n_events;
         ++cpuhw->n_added;
 
@@ -896,11 +849,65 @@ static void power_pmu_unthrottle(struct perf_event *event)
         local_irq_restore(flags);
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+void power_pmu_start_txn(const struct pmu *pmu)
+{
+        struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+        cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuhw->n_txn_start = cpuhw->n_events;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+void power_pmu_cancel_txn(const struct pmu *pmu)
+{
+        struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+        cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Commit group events scheduling transaction
+ * Perform the group schedulability test as a whole
+ * Return 0 if success
+ */
+int power_pmu_commit_txn(const struct pmu *pmu)
+{
+        struct cpu_hw_events *cpuhw;
+        long i, n;
+
+        if (!ppmu)
+                return -EAGAIN;
+        cpuhw = &__get_cpu_var(cpu_hw_events);
+        n = cpuhw->n_events;
+        if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
+                return -EAGAIN;
+        i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n);
+        if (i < 0)
+                return -EAGAIN;
+
+        for (i = cpuhw->n_txn_start; i < n; ++i)
+                cpuhw->event[i]->hw.config = cpuhw->events[i];
+
+        return 0;
+}
+
 struct pmu power_pmu = {
         .enable         = power_pmu_enable,
         .disable        = power_pmu_disable,
         .read           = power_pmu_read,
         .unthrottle     = power_pmu_unthrottle,
+        .start_txn      = power_pmu_start_txn,
+        .cancel_txn     = power_pmu_cancel_txn,
+        .commit_txn     = power_pmu_commit_txn,
 };
 
 /*
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1b16b9a3e49a..0441bbdadbd1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -532,25 +532,60 @@ void __init iSeries_time_init_early(void)
 }
 #endif /* CONFIG_PPC_ISERIES */
 
-#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_PPC32)
-DEFINE_PER_CPU(u8, perf_event_pending);
+#ifdef CONFIG_PERF_EVENTS
 
-void set_perf_event_pending(void)
+/*
+ * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
+ */
+#ifdef CONFIG_PPC64
+static inline unsigned long test_perf_event_pending(void)
 {
-        get_cpu_var(perf_event_pending) = 1;
-        set_dec(1);
-        put_cpu_var(perf_event_pending);
+        unsigned long x;
+
+        asm volatile("lbz %0,%1(13)"
+                : "=r" (x)
+                : "i" (offsetof(struct paca_struct, perf_event_pending)));
+        return x;
 }
 
+static inline void set_perf_event_pending_flag(void)
+{
+        asm volatile("stb %0,%1(13)" : :
+                "r" (1),
+                "i" (offsetof(struct paca_struct, perf_event_pending)));
+}
+
+static inline void clear_perf_event_pending(void)
+{
+        asm volatile("stb %0,%1(13)" : :
+                "r" (0),
+                "i" (offsetof(struct paca_struct, perf_event_pending)));
+}
+
+#else /* 32-bit */
+
+DEFINE_PER_CPU(u8, perf_event_pending);
+
+#define set_perf_event_pending_flag()   __get_cpu_var(perf_event_pending) = 1
 #define test_perf_event_pending()       __get_cpu_var(perf_event_pending)
 #define clear_perf_event_pending()      __get_cpu_var(perf_event_pending) = 0
 
-#else  /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */
+#endif /* 32 vs 64 bit */
+
+void set_perf_event_pending(void)
+{
+        preempt_disable();
+        set_perf_event_pending_flag();
+        set_dec(1);
+        preempt_enable();
+}
+
+#else  /* CONFIG_PERF_EVENTS */
 
 #define test_perf_event_pending()       0
 #define clear_perf_event_pending()
 
-#endif /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */
+#endif /* CONFIG_PERF_EVENTS */
 
 /*
  * For iSeries shared processors, we have to let the hypervisor
@@ -582,10 +617,6 @@ void timer_interrupt(struct pt_regs * regs)
         set_dec(DECREMENTER_MAX);
 
 #ifdef CONFIG_PPC32
-        if (test_perf_event_pending()) {
-                clear_perf_event_pending();
-                perf_event_do_pending();
-        }
         if (atomic_read(&ppc_n_lost_interrupts) != 0)
                 do_IRQ(regs);
 #endif
@@ -604,6 +635,11 @@ void timer_interrupt(struct pt_regs * regs)
 
         calculate_steal_time();
 
+        if (test_perf_event_pending()) {
+                clear_perf_event_pending();
+                perf_event_do_pending();
+        }
+
 #ifdef CONFIG_PPC_ISERIES
         if (firmware_has_feature(FW_FEATURE_ISERIES))
                 get_lppaca()->int_dword.fields.decr_int = 0;
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 2570fcc7665d..812312542e50 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -440,7 +440,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
         unsigned int gtlb_index;
 
         gtlb_index = kvmppc_get_gpr(vcpu, ra);
-        if (gtlb_index > KVM44x_GUEST_TLB_SIZE) {
+        if (gtlb_index >= KVM44x_GUEST_TLB_SIZE) {
                 printk("%s: index %d\n", __func__, gtlb_index);
                 kvmppc_dump_vcpu(vcpu);
                 return EMULATE_FAIL;