Merge tag 'perf-core-for-mingo-5.1-20190225' of git://git.kernel.org/…

…pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf annotate:

  Wei Li:

  - Fix getting source line failure

perf script:

  Andi Kleen:

  - Handle missing fields with -F +...

perf data:

  Jiri Olsa:

  - Prep work to support per-cpu files in a directory.

Intel PT:

  Adrian Hunter:

  - Improve thread_stack__no_call_return()

  - Hide x86 retpolines in thread stacks.

  - exported SQL viewer refactorings, new 'top calls' report..

  Alexander Shishkin:

  - Copy parent's address filter offsets on clone

  - Fix address filters for vmas with non-zero offset. Applies to
    ARM's CoreSight as well.

python scripts:

  Tony Jones:

  - Python3 support for several 'perf script' python scripts.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/events/intel/pt.c

@@ -1223,7 +1223,8 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 static void pt_event_addr_filters_sync(struct perf_event *event)
 {
 	struct perf_addr_filters_head *head = perf_event_addr_filters(event);
-	unsigned long msr_a, msr_b, *offs = event->addr_filters_offs;
+	unsigned long msr_a, msr_b;
+	struct perf_addr_filter_range *fr = event->addr_filter_ranges;
 	struct pt_filters *filters = event->hw.addr_filters;
 	struct perf_addr_filter *filter;
 	int range = 0;
@@ -1232,12 +1233,12 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		return;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		if (filter->path.dentry && !offs[range]) {
+		if (filter->path.dentry && !fr[range].start) {
 			msr_a = msr_b = 0;
 		} else {
 			/* apply the offset */
-			msr_a = filter->offset + offs[range];
-			msr_b = filter->size + msr_a - 1;
+			msr_a = fr[range].start;
+			msr_b = msr_a + fr[range].size - 1;
 		}
 
 		filters->filter[range].msr_a  = msr_a;

drivers/hwtracing/coresight/coresight-etm-perf.c

@@ -433,15 +433,16 @@ static int etm_addr_filters_validate(struct list_head *filters)
 static void etm_addr_filters_sync(struct perf_event *event)
 {
 	struct perf_addr_filters_head *head = perf_event_addr_filters(event);
-	unsigned long start, stop, *offs = event->addr_filters_offs;
+	unsigned long start, stop;
+	struct perf_addr_filter_range *fr = event->addr_filter_ranges;
 	struct etm_filters *filters = event->hw.addr_filters;
 	struct etm_filter *etm_filter;
 	struct perf_addr_filter *filter;
 	int i = 0;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		start = filter->offset + offs[i];
-		stop = start + filter->size;
+		start = fr[i].start;
+		stop = start + fr[i].size;
 		etm_filter = &filters->etm_filter[i];
 
 		switch (filter->action) {

include/linux/perf_event.h

@@ -495,6 +495,11 @@ struct perf_addr_filters_head {
 	unsigned int		nr_file_filters;
 };
 
+struct perf_addr_filter_range {
+	unsigned long		start;
+	unsigned long		size;
+};
+
 /**
  * enum perf_event_state - the states of an event:
  */
@@ -671,7 +676,7 @@ struct perf_event {
 	/* address range filters */
 	struct perf_addr_filters_head	addr_filters;
 	/* vma address array for file-based filders */
-	unsigned long			*addr_filters_offs;
+	struct perf_addr_filter_range	*addr_filter_ranges;
 	unsigned long			addr_filters_gen;
 
 	void (*destroy)(struct perf_event *);

kernel/events/core.c

@@ -1255,6 +1255,7 @@ static void put_ctx(struct perf_event_context *ctx)
  *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
  *	    mmap_sem
+ *	      perf_addr_filters_head::lock
  *
  *    cpu_hotplug_lock
  *      pmus_lock
@@ -2798,7 +2799,7 @@ static int perf_event_stop(struct perf_event *event, int restart)
  *
  * (p1) when userspace mappings change as a result of (1) or (2) or (3) below,
  *      we update the addresses of corresponding vmas in
- *	event::addr_filters_offs array and bump the event::addr_filters_gen;
+ *	event::addr_filter_ranges array and bump the event::addr_filters_gen;
  * (p2) when an event is scheduled in (pmu::add), it calls
  *      perf_event_addr_filters_sync() which calls pmu::addr_filters_sync()
  *      if the generation has changed since the previous call.
@@ -4445,7 +4446,7 @@ static void _free_event(struct perf_event *event)
 
 	perf_event_free_bpf_prog(event);
 	perf_addr_filters_splice(event, NULL);
-	kfree(event->addr_filters_offs);
+	kfree(event->addr_filter_ranges);
 
 	if (event->destroy)
 		event->destroy(event);
@@ -6694,7 +6695,8 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
 		if (filter->path.dentry) {
-			event->addr_filters_offs[count] = 0;
+			event->addr_filter_ranges[count].start = 0;
+			event->addr_filter_ranges[count].size = 0;
 			restart++;
 		}
 
@@ -7374,28 +7376,47 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 	return true;
 }
 
+static bool perf_addr_filter_vma_adjust(struct perf_addr_filter *filter,
+					struct vm_area_struct *vma,
+					struct perf_addr_filter_range *fr)
+{
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct file *file = vma->vm_file;
+
+	if (!perf_addr_filter_match(filter, file, off, vma_size))
+		return false;
+
+	if (filter->offset < off) {
+		fr->start = vma->vm_start;
+		fr->size = min(vma_size, filter->size - (off - filter->offset));
+	} else {
+		fr->start = vma->vm_start + filter->offset - off;
+		fr->size = min(vma->vm_end - fr->start, filter->size);
+	}
+
+	return true;
+}
+
 static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
 {
 	struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
 	struct vm_area_struct *vma = data;
-	unsigned long off = vma->vm_pgoff << PAGE_SHIFT, flags;
-	struct file *file = vma->vm_file;
 	struct perf_addr_filter *filter;
 	unsigned int restart = 0, count = 0;
+	unsigned long flags;
 
 	if (!has_addr_filter(event))
 		return;
 
-	if (!file)
+	if (!vma->vm_file)
 		return;
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		if (perf_addr_filter_match(filter, file, off,
-					     vma->vm_end - vma->vm_start)) {
-			event->addr_filters_offs[count] = vma->vm_start;
+		if (perf_addr_filter_vma_adjust(filter, vma,
+						&event->addr_filter_ranges[count]))
 			restart++;
-		}
 
 		count++;
 	}
@@ -8985,26 +9006,19 @@ static void perf_addr_filters_splice(struct perf_event *event,
  * @filter; if so, adjust filter's address range.
  * Called with mm::mmap_sem down for reading.
  */
-static unsigned long perf_addr_filter_apply(struct perf_addr_filter *filter,
-					    struct mm_struct *mm)
+static void perf_addr_filter_apply(struct perf_addr_filter *filter,
+				   struct mm_struct *mm,
+				   struct perf_addr_filter_range *fr)
 {
 	struct vm_area_struct *vma;
 
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		struct file *file = vma->vm_file;
-		unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
-		unsigned long vma_size = vma->vm_end - vma->vm_start;
-
-		if (!file)
+		if (!vma->vm_file)
 			continue;
 
-		if (!perf_addr_filter_match(filter, file, off, vma_size))
-			continue;
-
-		return vma->vm_start;
+		if (perf_addr_filter_vma_adjust(filter, vma, fr))
+			return;
 	}
-
-	return 0;
 }
 
 /*
@@ -9038,15 +9052,15 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		event->addr_filters_offs[count] = 0;
+		event->addr_filter_ranges[count].start = 0;
+		event->addr_filter_ranges[count].size = 0;
 
 		/*
 		 * Adjust base offset if the filter is associated to a binary
 		 * that needs to be mapped:
 		 */
 		if (filter->path.dentry)
-			event->addr_filters_offs[count] =
-				perf_addr_filter_apply(filter, mm);
+			perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
 
 		count++;
 	}
@@ -10320,14 +10334,28 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_pmu;
 
 	if (has_addr_filter(event)) {
-		event->addr_filters_offs = kcalloc(pmu->nr_addr_filters,
-						   sizeof(unsigned long),
-						   GFP_KERNEL);
-		if (!event->addr_filters_offs) {
+		event->addr_filter_ranges = kcalloc(pmu->nr_addr_filters,
+						    sizeof(struct perf_addr_filter_range),
+						    GFP_KERNEL);
+		if (!event->addr_filter_ranges) {
 			err = -ENOMEM;
 			goto err_per_task;
 		}
 
+		/*
+		 * Clone the parent's vma offsets: they are valid until exec()
+		 * even if the mm is not shared with the parent.
+		 */
+		if (event->parent) {
+			struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+
+			raw_spin_lock_irq(&ifh->lock);
+			memcpy(event->addr_filter_ranges,
+			       event->parent->addr_filter_ranges,
+			       pmu->nr_addr_filters * sizeof(struct perf_addr_filter_range));
+			raw_spin_unlock_irq(&ifh->lock);
+		}
+
 		/* force hw sync on the address filters */
 		event->addr_filters_gen = 1;
 	}
@@ -10346,7 +10374,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	return event;
 
 err_addr_filters:
-	kfree(event->addr_filters_offs);
+	kfree(event->addr_filter_ranges);
 
 err_per_task:
 	exclusive_event_destroy(event);

tools/perf/builtin-annotate.c

@@ -441,7 +441,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	}
 
 	if (total_nr_samples == 0) {
-		ui__error("The %s file has no samples!\n", session->data->file.path);
+		ui__error("The %s data has no samples!\n", session->data->path);
 		goto out;
 	}
 
@@ -578,7 +578,7 @@ int cmd_annotate(int argc, const char **argv)
 	if (quiet)
 		perf_quiet_option();
 
-	data.file.path = input_name;
+	data.path = input_name;
 
 	annotate.session = perf_session__new(&data, false, &annotate.tool);
 	if (annotate.session == NULL)

tools/perf/builtin-buildid-cache.c

@@ -416,8 +416,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		nsi = nsinfo__new(ns_id);
 
 	if (missing_filename) {
-		data.file.path = missing_filename;
-		data.force     = force;
+		data.path  = missing_filename;
+		data.force = force;
 
 		session = perf_session__new(&data, false, NULL);
 		if (session == NULL)

tools/perf/builtin-buildid-list.c

@@ -52,11 +52,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = {
-			.path = input_name,
-		},
-		.mode      = PERF_DATA_MODE_READ,
-		.force     = force,
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = force,
 	};
 
 	symbol__elf_init();

tools/perf/builtin-c2c.c

@@ -2750,8 +2750,8 @@ static int perf_c2c__report(int argc, const char **argv)
 	if (!input_name || !strlen(input_name))
 		input_name = "perf.data";
 
-	data.file.path = input_name;
-	data.force     = symbol_conf.force;
+	data.path  = input_name;
+	data.force = symbol_conf.force;
 
 	err = setup_display(display);
 	if (err)

tools/perf/builtin-diff.c

@@ -708,7 +708,7 @@ static void data__fprintf(void)
 
 	data__for_each_file(i, d)
 		fprintf(stdout, "#  [%d] %s %s\n",
-			d->idx, d->data.file.path,
+			d->idx, d->data.path,
 			!d->idx ? "(Baseline)" : "");
 
 	fprintf(stdout, "#\n");
@@ -779,14 +779,14 @@ static int __cmd_diff(void)
 	data__for_each_file(i, d) {
 		d->session = perf_session__new(&d->data, false, &tool);
 		if (!d->session) {
-			pr_err("Failed to open %s\n", d->data.file.path);
+			pr_err("Failed to open %s\n", d->data.path);
 			ret = -1;
 			goto out_delete;
 		}
 
 		ret = perf_session__process_events(d->session);
 		if (ret) {
-			pr_err("Failed to process %s\n", d->data.file.path);
+			pr_err("Failed to process %s\n", d->data.path);
 			goto out_delete;
 		}
 
@@ -1289,9 +1289,9 @@ static int data_init(int argc, const char **argv)
 	data__for_each_file(i, d) {
 		struct perf_data *data = &d->data;
 
-		data->file.path = use_default ? defaults[i] : argv[i];
-		data->mode      = PERF_DATA_MODE_READ,
-		data->force     = force,
+		data->path  = use_default ? defaults[i] : argv[i];
+		data->mode  = PERF_DATA_MODE_READ,
+		data->force = force,
 
 		d->idx  = i;
 	}

tools/perf/builtin-evlist.c

@@ -23,9 +23,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	struct perf_session *session;
 	struct perf_evsel *pos;
 	struct perf_data data = {
-		.file      = {
-			.path = file_name,
-		},
+		.path      = file_name,
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = details->force,
 	};

tools/perf/builtin-inject.c

@@ -770,10 +770,8 @@ int cmd_inject(int argc, const char **argv)
 		.input_name  = "-",
 		.samples = LIST_HEAD_INIT(inject.samples),
 		.output = {
-			.file      = {
-				.path = "-",
-			},
-			.mode      = PERF_DATA_MODE_WRITE,
+			.path = "-",
+			.mode = PERF_DATA_MODE_WRITE,
 		},
 	};
 	struct perf_data data = {
@@ -786,7 +784,7 @@ int cmd_inject(int argc, const char **argv)
 			    "Inject build-ids into the output stream"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
 			   "input file name"),
-		OPT_STRING('o', "output", &inject.output.file.path, "file",
+		OPT_STRING('o', "output", &inject.output.path, "file",
 			   "output file name"),
 		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
 			    "Merge sched-stat and sched-switch for getting events "
@@ -834,7 +832,7 @@ int cmd_inject(int argc, const char **argv)
 
 	inject.tool.ordered_events = inject.sched_stat;
 
-	data.file.path = inject.input_name;
+	data.path = inject.input_name;
 	inject.session = perf_session__new(&data, true, &inject.tool);
 	if (inject.session == NULL)
 		return -1;

tools/perf/builtin-kmem.c

@@ -1949,7 +1949,7 @@ int cmd_kmem(int argc, const char **argv)
 		return __cmd_record(argc, argv);
 	}
 
-	data.file.path = input_name;
+	data.path = input_name;
 
 	kmem_session = session = perf_session__new(&data, false, &perf_kmem);
 	if (session == NULL)