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
  ...

Documentation/ABI/testing/sysfs-bus-event_source-devices-events

@@ -29,7 +29,7 @@ Description:	Generic performance monitoring events
 
 What: 		/sys/devices/cpu/events/PM_1PLUS_PPC_CMPL
 		/sys/devices/cpu/events/PM_BRU_FIN
-		/sys/devices/cpu/events/PM_BRU_MPRED
+		/sys/devices/cpu/events/PM_BR_MPRED
 		/sys/devices/cpu/events/PM_CMPLU_STALL
 		/sys/devices/cpu/events/PM_CMPLU_STALL_BRU
 		/sys/devices/cpu/events/PM_CMPLU_STALL_DCACHE_MISS

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),

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,

kernel/events/core.c

@@ -947,8 +947,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 {
 	struct perf_event_context *ctx;
 
-	rcu_read_lock();
 retry:
+	/*
+	 * One of the few rules of preemptible RCU is that one cannot do
+	 * rcu_read_unlock() while holding a scheduler (or nested) lock when
+	 * part of the read side critical section was preemptible -- see
+	 * rcu_read_unlock_special().
+	 *
+	 * Since ctx->lock nests under rq->lock we must ensure the entire read
+	 * side critical section is non-preemptible.
+	 */
+	preempt_disable();
+	rcu_read_lock();
 	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
 		/*
@@ -964,6 +974,8 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 		raw_spin_lock_irqsave(&ctx->lock, *flags);
 		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
 			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			rcu_read_unlock();
+			preempt_enable();
 			goto retry;
 		}
 
@@ -973,6 +985,7 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 		}
 	}
 	rcu_read_unlock();
+	preempt_enable();
 	return ctx;
 }
 
@@ -1950,7 +1963,16 @@ static int __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	if (WARN_ON_ONCE(!ctx->is_active))
+	/*
+	 * There's a time window between 'ctx->is_active' check
+	 * in perf_event_enable function and this place having:
+	 *   - IRQs on
+	 *   - ctx->lock unlocked
+	 *
+	 * where the task could be killed and 'ctx' deactivated
+	 * by perf_event_exit_task.
+	 */
+	if (!ctx->is_active)
 		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
@@ -7465,7 +7487,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * child.
 		 */
 
-		child_ctx = alloc_perf_context(event->pmu, child);
+		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
 

tools/lib/lk/Makefile

@@ -3,6 +3,21 @@ include ../../scripts/Makefile.include
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
 
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
 # guard against environment variables
 LIB_H=
 LIB_OBJS=
@@ -14,7 +29,7 @@ LIB_OBJS += $(OUTPUT)debugfs.o
 LIBFILE = liblk.a
 
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
-EXTLIBS = -lpthread -lrt -lelf -lm
+EXTLIBS = -lelf -lpthread -lrt -lm
 ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
 

tools/perf/Documentation/Makefile

@@ -1,12 +1,6 @@
+include ../../scripts/Makefile.include
 include ../config/utilities.mak
 
-OUTPUT := ./
-ifeq ("$(origin O)", "command line")
-  ifneq ($(O),)
-	OUTPUT := $(O)/
-  endif
-endif
-
 MAN1_TXT= \
 	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
 		$(wildcard perf-*.txt)) \
@@ -150,7 +144,7 @@ NO_SUBDIR = :
 endif
 
 ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifndef V
+ifneq ($(V),1)
 	QUIET_ASCIIDOC	= @echo '   ' ASCIIDOC $@;
 	QUIET_XMLTO	= @echo '   ' XMLTO $@;
 	QUIET_DB2TEXI	= @echo '   ' DB2TEXI $@;
@@ -277,7 +271,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt
 
 $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 	$(QUIET_XMLTO)$(RM) $@ && \
-	$(XMLTO) -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+	$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
 
 $(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \

tools/perf/Documentation/examples.txt

@@ -66,7 +66,7 @@ Furthermore, these tracepoints can be used to sample the workload as
 well. For example the page allocations done by a 'git gc' can be
 captured the following way:
 
- titan:~/git> perf record -f -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -e kmem:mm_page_alloc -c 1 ./git gc
  Counting objects: 1148, done.
  Delta compression using up to 2 threads.
  Compressing objects: 100% (450/450), done.
@@ -120,7 +120,7 @@ Furthermore, call-graph sampling can be done too, of page
 allocations - to see precisely what kind of page allocations there
 are:
 
- titan:~/git> perf record -f -g -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -g -e kmem:mm_page_alloc -c 1 ./git gc
  Counting objects: 1148, done.
  Delta compression using up to 2 threads.
  Compressing objects: 100% (450/450), done.

tools/perf/Documentation/perf-record.txt

@@ -65,16 +65,10 @@ OPTIONS
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
+
 -D::
 --no-delay::
 	Collect data without buffering.
--A::
---append::
-	Append to the output file to do incremental profiling.
-
--f::
---force::
-	Overwrite existing data file. (deprecated)
 
 -c::
 --count=::

tools/perf/Makefile

@@ -121,17 +121,16 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
-LK_PATH=$(LK_DIR)
-
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(OUTPUT)$(LK_DIR)
+  LK_PATH=$(objtree)/lib/lk/
 else
   LK_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
+  LK_PATH=$(LK_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a

tools/perf/bench/mem-memcpy.c

@@ -111,11 +111,11 @@ static double timeval2double(struct timeval *ts)
 static void alloc_mem(void **dst, void **src, size_t length)
 {
 	*dst = zalloc(length);
-	if (!dst)
+	if (!*dst)
 		die("memory allocation failed - maybe length is too large?\n");
 
 	*src = zalloc(length);
-	if (!src)
+	if (!*src)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 

tools/perf/bench/mem-memset.c

@@ -111,7 +111,7 @@ static double timeval2double(struct timeval *ts)
 static void alloc_mem(void **dst, size_t length)
 {
 	*dst = zalloc(length);
-	if (!dst)
+	if (!*dst)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 

tools/perf/builtin-diff.c

@@ -607,7 +607,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 		input_new = "perf.data.guest";
 	}
 
-	symbol_conf.exclude_other = false;
 	if (symbol__init() < 0)
 		return -1;
 

tools/perf/builtin-kmem.c

@@ -708,7 +708,7 @@ static int parse_line_opt(const struct option *opt __maybe_unused,
 static int __cmd_record(int argc, const char **argv)
 {
 	const char * const record_args[] = {
-	"record", "-a", "-R", "-f", "-c", "1",
+	"record", "-a", "-R", "-c", "1",
 	"-e", "kmem:kmalloc",
 	"-e", "kmem:kmalloc_node",
 	"-e", "kmem:kfree",

tools/perf/builtin-lock.c

@@ -878,7 +878,7 @@ static int __cmd_report(void)
 static int __cmd_record(int argc, const char **argv)
 {
 	const char *record_args[] = {
-		"record", "-R", "-f", "-m", "1024", "-c", "1",
+		"record", "-R", "-m", "1024", "-c", "1",
 	};
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;