Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
  tracing: Fix compile issue for trace_sched_wakeup.c
  [S390] hardirq: remove pointless header file includes
  [IA64] Move local_softirq_pending() definition
  perf, powerpc: Fix power_pmu_event_init to not use event->ctx
  ftrace: Remove recursion between recordmcount and scripts/mod/empty
  jump_label: Add COND_STMT(), reducer wrappery
  perf: Optimize sw events
  perf: Use jump_labels to optimize the scheduler hooks
  jump_label: Add atomic_t interface
  jump_label: Use more consistent naming
  perf, hw_breakpoint: Fix crash in hw_breakpoint creation
  perf: Find task before event alloc
  perf: Fix task refcount bugs
  perf: Fix group moving
  irq_work: Add generic hardirq context callbacks
  perf_events: Fix transaction recovery in group_sched_in()
  perf_events: Fix bogus AMD64 generic TLB events
  perf_events: Fix bogus context time tracking
  tracing: Remove parent recording in latency tracer graph options
  tracing: Use one prologue for the preempt irqs off tracer function tracers
  ...

24 files changed, 2876 insertions, 1369 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 17046b6e7c9..e2c9d52cfe9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
             notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-            async.o range.o
+            async.o range.o jump_label.o
 obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
@@ -23,6 +23,7 @@ CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_perf_event.o = -pg
+CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -101,6 +102,7 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
diff --git a/kernel/exit.c b/kernel/exit.c
index 03120229db2..e2bdf37f9fd 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -149,9 +149,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
         struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
-#ifdef CONFIG_PERF_EVENTS
-        WARN_ON_ONCE(tsk->perf_event_ctxp);
-#endif
+        perf_event_delayed_put(tsk);
         trace_sched_process_free(tsk);
         put_task_struct(tsk);
 }
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index c7c2aed9e2d..2c9120f0afc 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -113,12 +113,12 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
  */
 static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
 {
-        struct perf_event_context *ctx = bp->ctx;
+        struct task_struct *tsk = bp->hw.bp_target;
         struct perf_event *iter;
         int count = 0;
 
         list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-                if (iter->ctx == ctx && find_slot_idx(iter) == type)
+                if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type)
                         count += hw_breakpoint_weight(iter);
         }
 
@@ -134,7 +134,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
                     enum bp_type_idx type)
 {
         int cpu = bp->cpu;
-        struct task_struct *tsk = bp->ctx->task;
+        struct task_struct *tsk = bp->hw.bp_target;
 
         if (cpu >= 0) {
                 slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -213,7 +213,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
                int weight)
 {
         int cpu = bp->cpu;
-        struct task_struct *tsk = bp->ctx->task;
+        struct task_struct *tsk = bp->hw.bp_target;
 
         /* Pinned counter cpu profiling */
         if (!tsk) {
@@ -433,8 +433,7 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
                             perf_overflow_handler_t triggered,
                             struct task_struct *tsk)
 {
-        return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
-                                                triggered);
+        return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -516,7 +515,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
         get_online_cpus();
         for_each_online_cpu(cpu) {
                 pevent = per_cpu_ptr(cpu_events, cpu);
-                bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+                bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
 
                 *pevent = bp;
 
@@ -566,6 +565,61 @@ static struct notifier_block hw_breakpoint_exceptions_nb = {
         .priority = 0x7fffffff
 };
 
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+        release_bp_slot(event);
+}
+
+static int hw_breakpoint_event_init(struct perf_event *bp)
+{
+        int err;
+
+        if (bp->attr.type != PERF_TYPE_BREAKPOINT)
+                return -ENOENT;
+
+        err = register_perf_hw_breakpoint(bp);
+        if (err)
+                return err;
+
+        bp->destroy = bp_perf_event_destroy;
+
+        return 0;
+}
+
+static int hw_breakpoint_add(struct perf_event *bp, int flags)
+{
+        if (!(flags & PERF_EF_START))
+                bp->hw.state = PERF_HES_STOPPED;
+
+        return arch_install_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_del(struct perf_event *bp, int flags)
+{
+        arch_uninstall_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_start(struct perf_event *bp, int flags)
+{
+        bp->hw.state = 0;
+}
+
+static void hw_breakpoint_stop(struct perf_event *bp, int flags)
+{
+        bp->hw.state = PERF_HES_STOPPED;
+}
+
+static struct pmu perf_breakpoint = {
+        .task_ctx_nr    = perf_sw_context, /* could eventually get its own */
+