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
  ...

1 files changed, 34 insertions, 2 deletions

diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 60308053fdb..0920212e615 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -14,6 +14,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/nmi.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
 #include <linux/slab.h>
@@ -29,6 +30,9 @@
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/nmi.h>
+
 struct nmi_desc {
 	spinlock_t lock;
 	struct list_head head;
@@ -82,6 +86,15 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 #define nmi_to_desc(type) (&nmi_desc[type])
 
+static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+static int __init nmi_warning_debugfs(void)
+{
+	debugfs_create_u64("nmi_longest_ns", 0644,
+			arch_debugfs_dir, &nmi_longest_ns);
+	return 0;
+}
+fs_initcall(nmi_warning_debugfs);
+
 static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
@@ -96,8 +109,27 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 	 * can be latched at any given time.  Walk the whole list
 	 * to handle those situations.
 	 */
-	list_for_each_entry_rcu(a, &desc->head, list)
-		handled += a->handler(type, regs);
+	list_for_each_entry_rcu(a, &desc->head, list) {
+		u64 before, delta, whole_msecs;
+		int decimal_msecs, thishandled;
+
+		before = local_clock();
+		thishandled = a->handler(type, regs);
+		handled += thishandled;
+		delta = local_clock() - before;
+		trace_nmi_handler(a->handler, (int)delta, thishandled);
+
+		if (delta < nmi_longest_ns)
+			continue;
+
+		nmi_longest_ns = delta;
+		whole_msecs = do_div(delta, (1000 * 1000));
+		decimal_msecs = do_div(delta, 1000) % 1000;
+		printk_ratelimited(KERN_INFO
+			"INFO: NMI handler (%ps) took too long to run: "
+			"%lld.%03d msecs\n", a->handler, whole_msecs,
+			decimal_msecs);
+	}
 
 	rcu_read_unlock();