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

Pull perf updates from Ingo Molnar:
 "This tree includes some late late perf items that missed the first
  round:

  tools:

   - Bash auto completion improvements, now we can auto complete the
     tools long options, tracepoint event names, etc, from Namhyung Kim.

   - Look up thread using tid instead of pid in 'perf sched'.

   - Move global variables into a perf_kvm struct, from David Ahern.

   - Hists refactorings, preparatory for improved 'diff' command, from
     Jiri Olsa.

   - Hists refactorings, preparatory for event group viewieng work, from
     Namhyung Kim.

   - Remove double negation on optional feature macro definitions, from
     Namhyung Kim.

   - Remove several cases of needless global variables, on most
     builtins.

   - misc fixes

  kernel:

   - sysfs support for IBS on AMD CPUs, from Robert Richter.

   - Support for an upcoming Intel CPU, the Xeon-Phi / Knights Corner
     HPC blade PMU, from Vince Weaver.

   - misc fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  perf: Fix perf_cgroup_switch for sw-events
  perf: Clarify perf_cpu_context::active_pmu usage by renaming it to ::unique_pmu
  perf/AMD/IBS: Add sysfs support
  perf hists: Add more helpers for hist entry stat
  perf hists: Move he->stat.nr_events initialization to a template
  perf hists: Introduce struct he_stat
  perf diff: Removing the total_period argument from output code
  perf tool: Add hpp interface to enable/disable hpp column
  perf tools: Removing hists pair argument from output path
  perf hists: Separate overhead and baseline columns
  perf diff: Refactor diff displacement possition info
  perf hists: Add struct hists pointer to struct hist_entry
  perf tools: Complete tracepoint event names
  perf/x86: Add support for Intel Xeon-Phi Knights Corner PMU
  perf evlist: Remove some unused methods
  perf evlist: Introduce add_newtp method
  perf kvm: Move global variables into a perf_kvm struct
  perf tools: Convert to BACKTRACE_SUPPORT
  perf tools: Long option completion support for each subcommands
  perf tools: Complete long option names of perf command
  ...

1 files changed, 12 insertions, 9 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index cda3ebd49e86..dbccf83c134d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -372,6 +372,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+                if (cpuctx->unique_pmu != pmu)
+                        continue; /* ensure we process each cpuctx once */
 
                 /*
                  * perf_cgroup_events says at least one
@@ -395,9 +397,10 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 
                         if (mode & PERF_CGROUP_SWIN) {
                                 WARN_ON_ONCE(cpuctx->cgrp);
-                                /* set cgrp before ctxsw in to
-                                 * allow event_filter_match() to not
-                                 * have to pass task around
+                                /*
+                                 * set cgrp before ctxsw in to allow
+                                 * event_filter_match() to not have to pass
+                                 * task around
                                  */
                                 cpuctx->cgrp = perf_cgroup_from_task(task);
                                 cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
@@ -4412,7 +4415,7 @@ static void perf_event_task_event(struct perf_task_event *task_event)
         rcu_read_lock();
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-                if (cpuctx->active_pmu != pmu)
+                if (cpuctx->unique_pmu != pmu)
                         goto next;
                 perf_event_task_ctx(&cpuctx->ctx, task_event);
 
@@ -4558,7 +4561,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
         rcu_read_lock();
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-                if (cpuctx->active_pmu != pmu)
+                if (cpuctx->unique_pmu != pmu)
                         goto next;
                 perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
@@ -4754,7 +4757,7 @@ got_name:
         rcu_read_lock();
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-                if (cpuctx->active_pmu != pmu)
+                if (cpuctx->unique_pmu != pmu)
                         goto next;
                 perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
                                         vma->vm_flags & VM_EXEC);
@@ -5855,8 +5858,8 @@ static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
 
                 cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 
-                if (cpuctx->active_pmu == old_pmu)
-                        cpuctx->active_pmu = pmu;
+                if (cpuctx->unique_pmu == old_pmu)
+                        cpuctx->unique_pmu = pmu;
         }
 }
 
@@ -5991,7 +5994,7 @@ skip_type:
                 cpuctx->ctx.pmu = pmu;
                 cpuctx->jiffies_interval = 1;
                 INIT_LIST_HEAD(&cpuctx->rotation_list);
-                cpuctx->active_pmu = pmu;
+                cpuctx->unique_pmu = pmu;
         }
 
 got_cpu_context: