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

…linux/kernel/git/tip/tip

Pull perf updates from Thomas Gleixner:
 "Perf updates and fixes:

  Kernel:
   - Handle events which have the bpf_event attribute set as side band
     events as they carry information about BPF programs.
   - Add missing switch-case fall-through comments

  Libraries:
   - Fix leaks and double frees in error code paths.
   - Prevent buffer overflows in libtraceevent

  Tools:
   - Improvements in handling Intel BT/PTS
   - Add BTF ELF markers to perf trace BPF programs to improve output
   - Support --time, --cpu, --pid and --tid filters for perf diff
   - Calculate the column width in perf annotate as the hardcoded 6
     characters for the instruction are not sufficient
   - Small fixes all over the place"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  perf/core: Mark expected switch fall-through
  perf/x86/intel/uncore: Fix client IMC events return huge result
  perf/ring_buffer: Use high order allocations for AUX buffers optimistically
  perf data: Force perf_data__open|close zero data->file.path
  perf session: Fix double free in perf_data__close
  perf evsel: Probe for precise_ip with simple attr
  perf tools: Read and store caps/max_precise in perf_pmu
  perf hist: Fix memory leak of srcline
  perf hist: Add error path into hist_entry__init
  perf c2c: Fix c2c report for empty numa node
  perf script python: Add Python3 support to intel-pt-events.py
  perf script python: Add Python3 support to event_analyzing_sample.py
  perf script python: add Python3 support to check-perf-trace.py
  perf script python: Add Python3 support to futex-contention.py
  perf script python: Remove mixed indentation
  perf diff: Support --pid/--tid filter options
  perf diff: Support --cpu filter option
  perf diff: Support --time filter option
  perf thread: Generalize function to copy from thread addr space from intel-bts code
  perf annotate: Calculate the max instruction name, align column to that
  ...

arch/x86/events/intel/uncore.c

@@ -732,6 +732,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 		/* fixed counters have event field hardcoded to zero */
 		hwc->config = 0ULL;
 	} else if (is_freerunning_event(event)) {
+		hwc->config = event->attr.config;
 		if (!check_valid_freerunning_event(box, event))
 			return -EINVAL;
 		event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;

arch/x86/events/intel/uncore.h

@@ -292,8 +292,8 @@ static inline
 unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
 					struct perf_event *event)
 {
-	unsigned int type = uncore_freerunning_type(event->attr.config);
-	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+	unsigned int type = uncore_freerunning_type(event->hw.config);
+	unsigned int idx = uncore_freerunning_idx(event->hw.config);
 	struct intel_uncore_pmu *pmu = box->pmu;
 
 	return pmu->type->freerunning[type].counter_base +
@@ -377,15 +377,15 @@ static inline
 unsigned int uncore_freerunning_bits(struct intel_uncore_box *box,
 				     struct perf_event *event)
 {
-	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int type = uncore_freerunning_type(event->hw.config);
 
 	return box->pmu->type->freerunning[type].bits;
 }
 
 static inline int uncore_num_freerunning(struct intel_uncore_box *box,
 					 struct perf_event *event)
 {
-	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int type = uncore_freerunning_type(event->hw.config);
 
 	return box->pmu->type->freerunning[type].num_counters;
 }
@@ -399,8 +399,8 @@ static inline int uncore_num_freerunning_types(struct intel_uncore_box *box,
 static inline bool check_valid_freerunning_event(struct intel_uncore_box *box,
 						 struct perf_event *event)
 {
-	unsigned int type = uncore_freerunning_type(event->attr.config);
-	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+	unsigned int type = uncore_freerunning_type(event->hw.config);
+	unsigned int idx = uncore_freerunning_idx(event->hw.config);
 
 	return (type < uncore_num_freerunning_types(box, event)) &&
 	       (idx < uncore_num_freerunning(box, event));

arch/x86/events/intel/uncore_snb.c

@@ -442,9 +442,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	event->hw.event_base = base;
-	event->hw.config = cfg;
 	event->hw.idx = idx;
 
+	/* Convert to standard encoding format for freerunning counters */
+	event->hw.config = ((cfg - 1) << 8) | 0x10ff;
+
 	/* no group validation needed, we have free running counters */
 
 	return 0;

kernel/events/core.c

@@ -4238,7 +4238,8 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch)
+	    attr->context_switch ||
+	    attr->bpf_event)
 		return true;
 	return false;
 }
@@ -9174,6 +9175,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 		case IF_SRC_KERNELADDR:
 		case IF_SRC_KERNEL:
 			kernel = 1;
+			/* fall through */
 
 		case IF_SRC_FILEADDR:
 		case IF_SRC_FILE:

kernel/events/ring_buffer.c

@@ -598,29 +598,27 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 {
 	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
 	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
-	int ret = -ENOMEM, max_order = 0;
+	int ret = -ENOMEM, max_order;
 
 	if (!has_aux(event))
 		return -EOPNOTSUPP;
 
-	if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) {
-		/*
-		 * We need to start with the max_order that fits in nr_pages,
-		 * not the other way around, hence ilog2() and not get_order.
-		 */
-		max_order = ilog2(nr_pages);
+	/*
+	 * We need to start with the max_order that fits in nr_pages,
+	 * not the other way around, hence ilog2() and not get_order.
+	 */
+	max_order = ilog2(nr_pages);
 
-		/*
-		 * PMU requests more than one contiguous chunks of memory
-		 * for SW double buffering
-		 */
-		if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
-		    !overwrite) {
-			if (!max_order)
-				return -EINVAL;
+	/*
+	 * PMU requests more than one contiguous chunks of memory
+	 * for SW double buffering
+	 */
+	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
+	    !overwrite) {
+		if (!max_order)
+			return -EINVAL;
 
-			max_order--;
-		}
+		max_order--;
 	}
 
 	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,

tools/lib/traceevent/event-parse.c

@@ -2457,7 +2457,7 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 static char *arg_eval (struct tep_print_arg *arg)
 {
 	long long val;
-	static char buf[20];
+	static char buf[24];
 
 	switch (arg->type) {
 	case TEP_PRINT_ATOM:

tools/perf/Documentation/perf-diff.txt

@@ -118,6 +118,62 @@ OPTIONS
 	sum of shown entries will be always 100%.  "absolute" means it retains
 	the original value before and after the filter is applied.
 
+--time::
+	Analyze samples within given time window. It supports time
+	percent with multiple time ranges. Time string is 'a%/n,b%/m,...'
+	or 'a%-b%,c%-%d,...'.
+
+	For example:
+
+	Select the second 10% time slice to diff:
+
+	  perf diff --time 10%/2
+
+	Select from 0% to 10% time slice to diff:
+
+	  perf diff --time 0%-10%
+
+	Select the first and the second 10% time slices to diff:
+
+	  perf diff --time 10%/1,10%/2
+
+	Select from 0% to 10% and 30% to 40% slices to diff:
+
+	  perf diff --time 0%-10%,30%-40%
+
+	It also supports analyzing samples within a given time window
+	<start>,<stop>. Times have the format seconds.microseconds. If 'start'
+	is not given (i.e., time string is ',x.y') then analysis starts at
+	the beginning of the file. If stop time is not given (i.e, time
+	string is 'x.y,') then analysis goes to the end of the file. Time string is
+	'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different
+	perf.data files.
+
+	For example, we get the timestamp information from 'perf script'.
+
+	  perf script -i perf.data.old
+	    mgen 13940 [000]  3946.361400: ...
+
+	  perf script -i perf.data
+	    mgen 13940 [000]  3971.150589 ...
+
+	  perf diff --time 3946.361400,:3971.150589,
+
+	It analyzes the perf.data.old from the timestamp 3946.361400 to
+	the end of perf.data.old and analyzes the perf.data from the
+	timestamp 3971.150589 to the end of perf.data.
+
+--cpu:: Only diff samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
+--pid=::
+	Only diff samples for given process ID (comma separated list).
+
+--tid=::
+	Only diff samples for given thread ID (comma separated list).
+
 COMPARISON
 ----------
 The comparison is governed by the baseline file. The baseline perf.data

tools/perf/arch/arm64/annotate/instructions.c

@@ -58,7 +58,7 @@ static int arm64_mov__parse(struct arch *arch __maybe_unused,
 }
 
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops);
+			  struct ins_operands *ops, int max_ins_name);
 
 static struct ins_ops arm64_mov_ops = {
 	.parse	   = arm64_mov__parse,

tools/perf/arch/s390/annotate/instructions.c

@@ -46,7 +46,7 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
 }
 
 static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops);
+			   struct ins_operands *ops, int max_ins_name);
 
 static struct ins_ops s390_call_ops = {
 	.parse	   = s390_call__parse,

tools/perf/builtin-c2c.c

@@ -2056,6 +2056,12 @@ static int setup_nodes(struct perf_session *session)
 		if (!set)
 			return -ENOMEM;
 
+		nodes[node] = set;
+
+		/* empty node, skip */
+		if (cpu_map__empty(map))
+			continue;
+
 		for (cpu = 0; cpu < map->nr; cpu++) {
 			set_bit(map->map[cpu], set);
 
@@ -2064,8 +2070,6 @@ static int setup_nodes(struct perf_session *session)
 
 			cpu2node[map->map[cpu]] = node;
 		}
-
-		nodes[node] = set;
 	}
 
 	setup_nodes_header();