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

Pull perf fixes from Thomas Gleixner:
 - fix for do_div() abuse on x86
 - locking fix in perf core
 - a pile of (build) fixes and cleanups in perf tools

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  perf/x86: Fix incorrect use of do_div() in NMI warning
  perf: Fix perf_lock_task_context() vs RCU
  perf: Remove WARN_ON_ONCE() check in __perf_event_enable() for valid scenario
  perf: Clone child context from parent context pmu
  perf script: Fix broken include in Context.xs
  perf tools: Fix -ldw/-lelf link test when static linking
  perf tools: Revert regression in configuration of Python support
  perf tools: Fix perf version generation
  perf stat: Fix per-socket output bug for uncore events
  perf symbols: Fix vdso list searching
  perf evsel: Fix missing increment in sample parsing
  perf tools: Update symbol_conf.nr_events when processing attribute events
  perf tools: Fix new_term() missing free on error path
  perf tools: Fix parse_events_terms() segfault on error path
  perf evsel: Fix count parameter to read call in event_format__new
  perf tools: fix a typo of a Power7 event name
  perf tools: Fix -x/--exclude-other option for report command
  perf evlist: Enhance perf_evlist__start_workload()
  perf record: Remove -f/--force option
  perf record: Remove -A/--append option
  ...

2 files changed, 10 insertions, 9 deletions

diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 13c3f0e..d1821b8 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -60,7 +60,7 @@
 #define	PME_PM_LD_REF_L1		0xc880
 #define	PME_PM_LD_MISS_L1		0x400f0
 #define	PME_PM_BRU_FIN			0x10068
-#define	PME_PM_BRU_MPRED		0x400f6
+#define	PME_PM_BR_MPRED			0x400f6
 
 #define PME_PM_CMPLU_STALL_FXU			0x20014
 #define PME_PM_CMPLU_STALL_DIV			0x40014
@@ -349,7 +349,7 @@ static int power7_generic_events[] = {
 	[PERF_COUNT_HW_CACHE_REFERENCES] =		PME_PM_LD_REF_L1,
 	[PERF_COUNT_HW_CACHE_MISSES] =			PME_PM_LD_MISS_L1,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PME_PM_BRU_FIN,
-	[PERF_COUNT_HW_BRANCH_MISSES] =			PME_PM_BRU_MPRED,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PME_PM_BR_MPRED,
 };
 
 #define C(x)	PERF_COUNT_HW_CACHE_##x
@@ -405,7 +405,7 @@ GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
 GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
 GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
 GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses,		BRU_MPRED);
+GENERIC_EVENT_ATTR(branch-misses,		BR_MPRED);
 
 POWER_EVENT_ATTR(CYC,				CYC);
 POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
@@ -414,7 +414,7 @@ POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
 POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
 POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
 POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
-POWER_EVENT_ATTR(BRU_MPRED,			BRU_MPRED);
+POWER_EVENT_ATTR(BR_MPRED,			BR_MPRED);
 
 POWER_EVENT_ATTR(CMPLU_STALL_FXU,		CMPLU_STALL_FXU);
 POWER_EVENT_ATTR(CMPLU_STALL_DIV,		CMPLU_STALL_DIV);
@@ -449,7 +449,7 @@ static struct attribute *power7_events_attr[] = {
 	GENERIC_EVENT_PTR(LD_REF_L1),
 	GENERIC_EVENT_PTR(LD_MISS_L1),
 	GENERIC_EVENT_PTR(BRU_FIN),
-	GENERIC_EVENT_PTR(BRU_MPRED),
+	GENERIC_EVENT_PTR(BR_MPRED),
 
 	POWER_EVENT_PTR(CYC),
 	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
@@ -458,7 +458,7 @@ static struct attribute *power7_events_attr[] = {
 	POWER_EVENT_PTR(LD_REF_L1),
 	POWER_EVENT_PTR(LD_MISS_L1),
 	POWER_EVENT_PTR(BRU_FIN),
-	POWER_EVENT_PTR(BRU_MPRED),
+	POWER_EVENT_PTR(BR_MPRED),
 
 	POWER_EVENT_PTR(CMPLU_STALL_FXU),
 	POWER_EVENT_PTR(CMPLU_STALL_DIV),
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 0920212..ba77ebc 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -111,7 +111,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 	 */
 	list_for_each_entry_rcu(a, &desc->head, list) {
 		u64 before, delta, whole_msecs;
-		int decimal_msecs, thishandled;
+		int remainder_ns, decimal_msecs, thishandled;
 
 		before = local_clock();
 		thishandled = a->handler(type, regs);
@@ -123,8 +123,9 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 			continue;
 
 		nmi_longest_ns = delta;
-		whole_msecs = do_div(delta, (1000 * 1000));
-		decimal_msecs = do_div(delta, 1000) % 1000;
+		whole_msecs = delta;
+		remainder_ns = do_div(whole_msecs, (1000 * 1000));
+		decimal_msecs = remainder_ns / 1000;
 		printk_ratelimited(KERN_INFO
 			"INFO: NMI handler (%ps) took too long to run: "
 			"%lld.%03d msecs\n", a->handler, whole_msecs,