Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-6

Conflicts:
	include/trace/ftrace.h
	kernel/trace/trace_kprobe.c

Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

18 files changed, 849 insertions, 910 deletions

diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index da5e13975531..e5c0244962b0 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -205,9 +205,12 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
          * No lock is needed, since the task isn't on tasklist yet,
          * so it can't be moved to another cgroup, which means the
          * freezer won't be removed and will be valid during this
-         * function call.
+         * function call.  Nevertheless, apply RCU read-side critical
+         * section to suppress RCU lockdep false positives.
          */
+        rcu_read_lock();
         freezer = task_freezer(task);
+        rcu_read_unlock();
 
         /*
          * The root cgroup is non-freezable, so we can skip the
diff --git a/kernel/fork.c b/kernel/fork.c
index 44b0791b0a2e..5d3592deaf71 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1111,9 +1111,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->memcg_batch.do_batch = 0;
         p->memcg_batch.memcg = NULL;
 #endif
-
-        p->bts = NULL;
-
         p->stack_start = stack_start;
 
         /* Perform scheduler related setup. Assign this task to a CPU. */
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 03808ed342a6..7a56b22e0602 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -40,23 +40,29 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
 
 #include <linux/hw_breakpoint.h>
 
+
 /*
  * Constraints data
  */
 
 /* Number of pinned cpu breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
 
 /* Number of pinned task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
+static DEFINE_PER_CPU(unsigned int *, nr_task_bp_pinned[TYPE_MAX]);
 
 /* Number of non-pinned cpu/task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
+
+static int nr_slots[TYPE_MAX];
+
+static int constraints_initialized;
 
 /* Gather the number of total pinned and un-pinned bp in a cpuset */
 struct bp_busy_slots {
@@ -67,16 +73,29 @@ struct bp_busy_slots {
 /* Serialize accesses to the above constraints */
 static DEFINE_MUTEX(nr_bp_mutex);
 
+__weak int hw_breakpoint_weight(struct perf_event *bp)
+{
+        return 1;
+}
+
+static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
+{
+        if (bp->attr.bp_type & HW_BREAKPOINT_RW)
+                return TYPE_DATA;
+
+        return TYPE_INST;
+}
+
 /*
  * Report the maximum number of pinned breakpoints a task
  * have in this cpu
  */
-static unsigned int max_task_bp_pinned(int cpu)
+static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 {
         int i;
-        unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+        unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 
-        for (i = HBP_NUM -1; i >= 0; i--) {
+        for (i = nr_slots[type] - 1; i >= 0; i--) {
                 if (tsk_pinned[i] > 0)
                         return i + 1;
         }
@@ -84,7 +103,7 @@ static unsigned int max_task_bp_pinned(int cpu)
         return 0;
 }
 
-static int task_bp_pinned(struct task_struct *tsk)
+static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type)
 {
         struct perf_event_context *ctx = tsk->perf_event_ctxp;
         struct list_head *list;
@@ -105,7 +124,8 @@ static int task_bp_pinned(struct task_struct *tsk)
          */
         list_for_each_entry(bp, list, event_entry) {
                 if (bp->attr.type == PERF_TYPE_BREAKPOINT)
-                        count++;
+                        if (find_slot_idx(bp) == type)
+                                count += hw_breakpoint_weight(bp);
         }
 
         raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -118,18 +138,19 @@ static int task_bp_pinned(struct task_struct *tsk)
  * a given cpu (cpu > -1) or in all of them (cpu = -1).
  */
 static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
+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;
 
         if (cpu >= 0) {
-                slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+                slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
                 if (!tsk)
-                        slots->pinned += max_task_bp_pinned(cpu);
+                        slots->pinned += max_task_bp_pinned(cpu, type);
                 else
-                        slots->pinned += task_bp_pinned(tsk);
-                slots->flexible = per_cpu(nr_bp_flexible, cpu);
+                        slots->pinned += task_bp_pinned(tsk, type);
+                slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
                 return;