4 files changed, 70 insertions, 55 deletions

diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index f0d343c3b956..7ae128b19d3f 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -25,7 +25,7 @@ extern int atomic_cmpxchg(atomic_t *, int, int);
 extern int atomic_add_unless(atomic_t *, int, int);
 extern void atomic_set(atomic_t *, int);
 
-#define atomic_read(v)          ((v)->counter)
+#define atomic_read(v)          (*(volatile int *)&(v)->counter)
 
 #define atomic_add(i, v)        ((void)__atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)        ((void)__atomic_add_return(-(int)(i), (v)))
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2e48009989e..2050ca02c423 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -13,8 +13,8 @@
 #define ATOMIC_INIT(i)          { (i) }
 #define ATOMIC64_INIT(i)        { (i) }
 
-#define atomic_read(v)          ((v)->counter)
-#define atomic64_read(v)        ((v)->counter)
+#define atomic_read(v)          (*(volatile int *)&(v)->counter)
+#define atomic64_read(v)        (*(volatile long *)&(v)->counter)
 
 #define atomic_set(v, i)        (((v)->counter) = i)
 #define atomic64_set(v, i)      (((v)->counter) = i)
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index e72ac9cdfb98..766121a67a24 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #ifdef ULTRA_HAS_POPULATION_COUNT
 
-static inline unsigned int hweight64(unsigned long w)
+static inline unsigned int __arch_hweight64(unsigned long w)
 {
         unsigned int res;
 
@@ -52,7 +52,7 @@ static inline unsigned int hweight64(unsigned long w)
         return res;
 }
 
-static inline unsigned int hweight32(unsigned int w)
+static inline unsigned int __arch_hweight32(unsigned int w)
 {
         unsigned int res;
 
@@ -60,7 +60,7 @@ static inline unsigned int hweight32(unsigned int w)
         return res;
 }
 
-static inline unsigned int hweight16(unsigned int w)
+static inline unsigned int __arch_hweight16(unsigned int w)
 {
         unsigned int res;
 
@@ -68,7 +68,7 @@ static inline unsigned int hweight16(unsigned int w)
         return res;
 }
 
-static inline unsigned int hweight8(unsigned int w)
+static inline unsigned int __arch_hweight8(unsigned int w)
 {
         unsigned int res;
 
@@ -78,9 +78,10 @@ static inline unsigned int hweight8(unsigned int w)
 
 #else
 
-#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/arch_hweight.h>
 
 #endif
+#include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index e2771939341d..cf4ce263ff81 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -91,6 +91,8 @@ struct cpu_hw_events {
 
         /* Enabled/disable state.  */
         int                     enabled;
+
+        unsigned int            group_flag;
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
 
@@ -980,53 +982,6 @@ 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);
-}
-
-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 *cpuc = &__get_cpu_var(cpu_hw_events);
-        struct perf_event *sub;
-        int n0, n;
-
-        if (!sparc_pmu)
-                return 0;
-
-        n0 = cpuc->n_events;
-        n = collect_events(group_leader, perf_max_events - n0,
-                           &cpuc->event[n0], &cpuc->events[n0],
-                           &cpuc->current_idx[n0]);
-        if (n < 0)
-                return -EAGAIN;
-        if (check_excludes(cpuc->event, n0, n))
-                return -EINVAL;
-        if (sparc_check_constraints(cpuc->event, cpuc->events, n + n0))
-                return -EAGAIN;
-        cpuc->n_events = n0 + n;
-        cpuc->n_added += n;
-
-        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;
-}
-
 static int sparc_pmu_enable(struct perf_event *event)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1044,11 +999,20 @@ static int sparc_pmu_enable(struct perf_event *event)
         cpuc->events[n0] = event->hw.event_base;
         cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+        /*
+         * 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 (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+                goto nocheck;
+
         if (check_excludes(cpuc->event, n0, 1))
                 goto out;
         if (sparc_check_constraints(cpuc->event, cpuc->events, n0 + 1))
                 goto out;
 
+nocheck:
         cpuc->n_events++;
         cpuc->n_added++;
 
@@ -1128,11 +1092,61 @@ static int __hw_perf_event_init(struct perf_event *event)
         return 0;
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+static void sparc_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;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+static void sparc_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
+ */
+static int sparc_pmu_commit_txn(const struct pmu *pmu)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        int n;
+
+        if (!sparc_pmu)
+                return -EINVAL;
+
+        cpuc = &__get_cpu_var(cpu_hw_events);
+        n = cpuc->n_events;
+        if (check_excludes(cpuc->event, 0, n))
+                return -EINVAL;
+        if (sparc_check_constraints(cpuc->event, cpuc->events, n))
+                return -EAGAIN;
+
+        return 0;
+}
+
 static const struct pmu pmu = {
         .enable         = sparc_pmu_enable,
         .disable        = sparc_pmu_disable,
         .read           = sparc_pmu_read,
         .unthrottle     = sparc_pmu_unthrottle,
+        .start_txn      = sparc_pmu_start_txn,
+        .cancel_txn     = sparc_pmu_cancel_txn,
+        .commit_txn     = sparc_pmu_commit_txn,
 };
 
 const struct pmu *hw_perf_event_init(struct perf_event *event)