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

Pull perf updates from Ingo Molnar:
 "Kernel improvements:

   - watchdog driver improvements by Li Zefan
   - Power7 CPI stack events related improvements by Sukadev Bhattiprolu
   - event multiplexing via hrtimers and other improvements by Stephane
     Eranian
   - kernel stack use optimization by Andrew Hunter
   - AMD IOMMU uncore PMU support by Suravee Suthikulpanit
   - NMI handling rate-limits by Dave Hansen
   - various hw_breakpoint fixes by Oleg Nesterov
   - hw_breakpoint overflow period sampling and related signal handling
     fixes by Jiri Olsa
   - Intel Haswell PMU support by Andi Kleen

  Tooling improvements:

   - Reset SIGTERM handler in workload child process, fix from David
     Ahern.
   - Makefile reorganization, prep work for Kconfig patches, from Jiri
     Olsa.
   - Add automated make test suite, from Jiri Olsa.
   - Add --percent-limit option to 'top' and 'report', from Namhyung
     Kim.
   - Sorting improvements, from Namhyung Kim.
   - Expand definition of sysfs format attribute, from Michael Ellerman.

  Tooling fixes:

   - 'perf tests' fixes from Jiri Olsa.
   - Make Power7 CPI stack events available in sysfs, from Sukadev
     Bhattiprolu.
   - Handle death by SIGTERM in 'perf record', fix from David Ahern.
   - Fix printing of perf_event_paranoid message, from David Ahern.
   - Handle realloc failures in 'perf kvm', from David Ahern.
   - Fix divide by 0 in variance, from David Ahern.
   - Save parent pid in thread struct, from David Ahern.
   - Handle JITed code in shared memory, from Andi Kleen.
   - Fixes for 'perf diff', from Jiri Olsa.
   - Remove some unused struct members, from Jiri Olsa.
   - Add missing liblk.a dependency for python/perf.so, fix from Jiri
     Olsa.
   - Respect CROSS_COMPILE in liblk.a, from Rabin Vincent.
   - No need to do locking when adding hists in perf report, only 'top'
     needs that, from Namhyung Kim.
   - Fix alignment of symbol column in in the hists browser (top,
     report) when -v is given, from NAmhyung Kim.
   - Fix 'perf top' -E option behavior, from Namhyung Kim.
   - Fix bug in isupper() and islower(), from Sukadev Bhattiprolu.
   - Fix compile errors in bp_signal 'perf test', from Sukadev
     Bhattiprolu.

  ... and more things"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (102 commits)
  perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
  perf/x86: Fix shared register mutual exclusion enforcement
  perf/x86/intel: Support full width counting
  x86: Add NMI duration tracepoints
  perf: Drop sample rate when sampling is too slow
  x86: Warn when NMI handlers take large amounts of time
  hw_breakpoint: Introduce "struct bp_cpuinfo"
  hw_breakpoint: Simplify *register_wide_hw_breakpoint()
  hw_breakpoint: Introduce cpumask_of_bp()
  hw_breakpoint: Simplify the "weight" usage in toggle_bp_slot() paths
  hw_breakpoint: Simplify list/idx mess in toggle_bp_slot() paths
  perf/x86/intel: Add mem-loads/stores support for Haswell
  perf/x86/intel: Support Haswell/v4 LBR format
  perf/x86/intel: Move NMI clearing to end of PMI handler
  perf/x86/intel: Add Haswell PEBS support
  perf/x86/intel: Add simple Haswell PMU support
  perf/x86/intel: Add Haswell PEBS record support
  perf/x86/intel: Fix sparse warning
  perf/x86/amd: AMD IOMMU Performance Counter PERF uncore PMU implementation
  perf/x86/amd: Add IOMMU Performance Counter resource management
  ...

3 files changed, 65 insertions, 5 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c5b6dbf9c2fc..50b3efd14d29 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -73,13 +73,18 @@ struct perf_raw_record {
  *
  * support for mispred, predicted is optional. In case it
  * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
  */
 struct perf_branch_entry {
         __u64   from;
         __u64   to;
         __u64   mispred:1,  /* target mispredicted */
                 predicted:1,/* target predicted */
-                reserved:62;
+                in_tx:1,    /* in transaction */
+                abort:1,    /* transaction abort */
+                reserved:60;
 };
 
 /*
@@ -113,6 +118,8 @@ struct hw_perf_event_extra {
         int             idx;    /* index in shared_regs->regs[] */
 };
 
+struct event_constraint;
+
 /**
  * struct hw_perf_event - performance event hardware details:
  */
@@ -131,6 +138,8 @@ struct hw_perf_event {
 
                         struct hw_perf_event_extra extra_reg;
                         struct hw_perf_event_extra branch_reg;
+
+                        struct event_constraint *constraint;
                 };
                 struct { /* software */
                         struct hrtimer  hrtimer;
@@ -188,12 +197,13 @@ struct pmu {
 
         struct device                   *dev;
         const struct attribute_group    **attr_groups;
-        char                            *name;
+        const char                      *name;
         int                             type;
 
         int * __percpu                  pmu_disable_count;
         struct perf_cpu_context * __percpu pmu_cpu_context;
         int                             task_ctx_nr;
+        int                             hrtimer_interval_ms;
 
         /*
          * Fully disable/enable this PMU, can be used to protect from the PMI
@@ -500,8 +510,9 @@ struct perf_cpu_context {
         struct perf_event_context       *task_ctx;
         int                             active_oncpu;
         int                             exclusive;
+        struct hrtimer                  hrtimer;
+        ktime_t                         hrtimer_interval;
         struct list_head                rotation_list;
-        int                             jiffies_interval;
         struct pmu                      *unique_pmu;
         struct perf_cgroup              *cgrp;
 };
@@ -517,7 +528,7 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-extern int perf_pmu_register(struct pmu *pmu, char *name, int type);
+extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
 extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern int perf_num_counters(void);
@@ -695,10 +706,17 @@ static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
+extern int sysctl_perf_cpu_time_max_percent;
+
+extern void perf_sample_event_took(u64 sample_len_ns);
 
 extern int perf_proc_update_handler(struct ctl_table *table, int write,
                 void __user *buffer, size_t *lenp,
                 loff_t *ppos);
+extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+                void __user *buffer, size_t *lenp,
+                loff_t *ppos);
+
 
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
@@ -742,6 +760,7 @@ extern unsigned int perf_output_skip(struct perf_output_handle *handle,
                                      unsigned int len);
 extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
+extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern int __perf_event_disable(void *info);
@@ -781,6 +800,7 @@ static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)                                { }
 static inline int  perf_swevent_get_recursion_context(void)             { return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)         { }
+static inline u64 perf_swevent_set_period(struct perf_event *event)     { return 0; }
 static inline void perf_event_enable(struct perf_event *event)          { }
 static inline void perf_event_disable(struct perf_event *event)         { }
 static inline int __perf_event_disable(void *info)                      { return -1; }
diff --git a/include/trace/events/nmi.h b/include/trace/events/nmi.h
new file mode 100644
index 000000000000..da3ee96b8d03
--- /dev/null
+++ b/include/trace/events/nmi.h
@@ -0,0 +1,37 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nmi
+
+#if !defined(_TRACE_NMI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NMI_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(nmi_handler,
+
+        TP_PROTO(void *handler, s64 delta_ns, int handled),
+
+        TP_ARGS(handler, delta_ns, handled),
+
+        TP_STRUCT__entry(
+                __field(        void *,         handler )
+                __field(        s64,            delta_ns)
+                __field(        int,            handled )
+        ),
+
+        TP_fast_assign(
+                __entry->handler = handler;
+                __entry->delta_ns = delta_ns;
+                __entry->handled = handled;
+        ),
+
+        TP_printk("%ps() delta_ns: %lld handled: %d",
+                __entry->handler,
+                __entry->delta_ns,
+                __entry->handled)
+);
+
+#endif /* _TRACE_NMI_H */
+
+/* This part ust be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index fb104e51496e..0b1df41691e8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -157,8 +157,11 @@ enum perf_branch_sample_type {
         PERF_SAMPLE_BRANCH_ANY_CALL     = 1U << 4, /* any call branch */
         PERF_SAMPLE_BRANCH_ANY_RETURN   = 1U << 5, /* any return branch */
         PERF_SAMPLE_BRANCH_IND_CALL     = 1U << 6, /* indirect calls */
+        PERF_SAMPLE_BRANCH_ABORT_TX     = 1U << 7, /* transaction aborts */
+        PERF_SAMPLE_BRANCH_IN_TX        = 1U << 8, /* in transaction */
+        PERF_SAMPLE_BRANCH_NO_TX        = 1U << 9, /* not in transaction */
 
-        PERF_SAMPLE_BRANCH_MAX          = 1U << 7, /* non-ABI */
+        PERF_SAMPLE_BRANCH_MAX          = 1U << 10, /* non-ABI */
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \