Merge tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "New features:

  perf ftrace:

   - Add -n/--use-nsec option to the 'latency' subcommand.

     Default: usecs:

     $ sudo perf ftrace latency -T dput -a sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |    2098375 | #############################  |
          1 - 2    us |         61 |                                |
          2 - 4    us |         33 |                                |
          4 - 8    us |         13 |                                |
          8 - 16   us |        124 |                                |
         16 - 32   us |        123 |                                |
         32 - 64   us |          1 |                                |
         64 - 128  us |          0 |                                |
        128 - 256  us |          1 |                                |
        256 - 512  us |          0 |                                |

     Better granularity with nsec:

     $ sudo perf ftrace latency -T dput -a -n sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |          0 |                                |
          1 - 2    ns |          0 |                                |
          2 - 4    ns |          0 |                                |
          4 - 8    ns |          0 |                                |
          8 - 16   ns |          0 |                                |
         16 - 32   ns |          0 |                                |
         32 - 64   ns |          0 |                                |
         64 - 128  ns |    1163434 | ##############                 |
        128 - 256  ns |     914102 | #############                  |
        256 - 512  ns |        884 |                                |
        512 - 1024 ns |        613 |                                |
          1 - 2    us |         31 |                                |
          2 - 4    us |         17 |                                |
          4 - 8    us |          7 |                                |
          8 - 16   us |        123 |                                |
         16 - 32   us |         83 |                                |

  perf lock:

   - Add -c/--combine-locks option to merge lock instances in the same
     class into a single entry.

     # perf lock report -c
                    Name acquired contended avg wait(ns) total wait(ns) max wait(ns) min wait(ns)

           rcu_read_lock   251225         0            0              0            0            0
      hrtimer_bases.lock    39450         0            0              0            0            0
     &sb->s_type->i_l...    10301         1          662            662          662          662
        ptlock_ptr(page)    10173         2          701           1402          760          642
     &(ei->i_block_re...     8732         0            0              0            0            0
            &xa->xa_lock     8088         0            0              0            0            0
             &base->lock     6705         0            0              0            0            0
             &p->pi_lock     5549         0            0              0            0            0
     &dentry->d_lockr...     5010         4         1274           5097         1844          789
               &ep->lock     3958         0            0              0            0            0

      - Add -F/--field option to customize the list of fields to output:

     $ perf lock report -F contended,wait_max -k avg_wait
                     Name contended max wait(ns) avg wait(ns)

           slock-AF_INET6         1        23543        23543
        &lruvec->lru_lock         5        18317        11254
           slock-AF_INET6         1        10379        10379
               rcu_node_1         1         2104         2104
      &dentry->d_lockr...         1         1844         1844
      &dentry->d_lockr...         1         1672         1672
         &newf->file_lock        15         2279         1025
      &dentry->d_lockr...         1          792          792

   - Add --synth=no option for record, as there is no need to symbolize,
     lock names comes from the tracepoints.

  perf record:

   - Threaded recording, opt-in, via the new --threads command line
     option.

   - Improve AMD IBS (Instruction-Based Sampling) error handling
     messages.

  perf script:

   - Add 'brstackinsnlen' field (use it with -F) for branch stacks.

   - Output branch sample type in 'perf script'.

  perf report:

   - Add "addr_from" and "addr_to" sort dimensions.

   - Print branch stack entry type in 'perf report --dump-raw-trace'

   - Fix symbolization for chrooted workloads.

  Hardware tracing:

  Intel PT:

   - Add CFE (Control Flow Event) and EVD (Event Data) packets support.

   - Add MODE.Exec IFLAG bit support.

     Explanation about these features from the "Intel® 64 and IA-32
     architectures software developer’s manual combined volumes: 1, 2A,
     2B, 2C, 2D, 3A, 3B, 3C, 3D, and 4" PDF at:

        https://cdrdv2.intel.com/v1/dl/getContent/671200

     At page 3951:
      "32.2.4

       Event Trace is a capability that exposes details about the
       asynchronous events, when they are generated, and when their
       corresponding software event handler completes execution. These
       include:

        o Interrupts, including NMI and SMI, including the interrupt
          vector when defined.

        o Faults, exceptions including the fault vector.

           - Page faults additionally include the page fault address,
             when in context.

        o Event handler returns, including IRET and RSM.

        o VM exits and VM entries.¹

           - VM exits include the values written to the “exit reason”
             and “exit qualification” VMCS fields. INIT and SIPI events.

        o TSX aborts, including the abort status returned for the RTM
          instructions.

        o Shutdown.

       Additionally, it provides indication of the status of the
       Interrupt Flag (IF), to indicate when interrupts are masked"

  ARM CoreSight:

   - Use advertised caps/min_interval as default sample_period on ARM
     spe.

   - Update deduction of TRCCONFIGR register for branch broadcast on
     ARM's CoreSight ETM.

  Vendor Events (JSON):

  Intel:

   - Update events and metrics for: Alderlake, Broadwell, Broadwell DE,
     BroadwellX, CascadelakeX, Elkhartlake, Bonnell, Goldmont,
     GoldmontPlus, Westmere EP-DP, Haswell, HaswellX, Icelake, IcelakeX,
     Ivybridge, Ivytown, Jaketown, Knights Landing, Nehalem EP,
     Sandybridge, Silvermont, Skylake, Skylake Server, SkylakeX,
     Tigerlake, TremontX, Westmere EP-SP, and Westmere EX.

  ARM:

   - Add support for HiSilicon CPA PMU aliasing.

  perf stat:

   - Fix forked applications enablement of counters.

   - The 'slots' should only be printed on a different order than the
     one specified on the command line when 'topdown' events are
     present, fix it.

  Miscellaneous:

   - Sync msr-index, cpufeatures header files with the kernel sources.

   - Stop using some deprecated libbpf APIs in 'perf trace'.

   - Fix some spelling mistakes.

   - Refactor the maps pointers usage to pave the way for using refcount
     debugging.

   - Only offer the --tui option on perf top, report and annotate when
     perf was built with libslang.

   - Don't mention --to-ctf in 'perf data --help' when not linking with
     the required library, libbabeltrace.

   - Use ARRAY_SIZE() instead of ad hoc equivalent, spotted by
     array_size.cocci.

   - Enhance the matching of sub-commands abbreviations:
	'perf c2c rec' -> 'perf c2c record'
	'perf c2c recport -> error

   - Set build-id using build-id header on new mmap records.

   - Fix generation of 'perf --version' string.

  perf test:

   - Add test for the arm_spe event.

   - Add test to check unwinding using fame-pointer (fp) mode on arm64.

   - Make metric testing more robust in 'perf test'.

   - Add error message for unsupported branch stack cases.

  libperf:

   - Add API for allocating new thread map array.

   - Fix typo in perf_evlist__open() failure error messages in libperf
     tests.

  perf c2c:

   - Replace bitmap_weight() with bitmap_empty() where appropriate"

* tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (143 commits)
  perf evsel: Improve AMD IBS (Instruction-Based Sampling) error handling messages
  perf python: Add perf_env stubs that will be needed in evsel__open_strerror()
  perf tools: Enhance the matching of sub-commands abbreviations
  libperf tests: Fix typo in perf_evlist__open() failure error messages
  tools arm64: Import cputype.h
  perf lock: Add -F/--field option to control output
  perf lock: Extend struct lock_key to have print function
  perf lock: Add --synth=no option for record
  tools headers cpufeatures: Sync with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  perf stat: Fix forked applications enablement of counters
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf evsel: Make evsel__env() always return a valid env
  perf build-id: Fix spelling mistake "Cant" -> "Can't"
  perf header: Fix spelling mistake "could't" -> "couldn't"
  perf script: Add 'brstackinsnlen' for branch stacks
  perf parse-events: Move slots only with topdown
  perf ftrace latency: Update documentation
  perf ftrace latency: Add -n/--use-nsec option
  perf tools: Fix version kernel tag
  ...

1 files changed, 403 insertions, 0 deletions

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
new file mode 100644
index 000000000000..37bd5b40000d
--- /dev/null
+++ b/tools/perf/util/maps.c
@@ -0,0 +1,403 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/zalloc.h>
+#include "debug.h"
+#include "dso.h"
+#include "map.h"
+#include "maps.h"
+#include "thread.h"
+#include "ui/ui.h"
+#include "unwind.h"
+
+static void __maps__insert(struct maps *maps, struct map *map);
+
+static void maps__init(struct maps *maps, struct machine *machine)
+{
+	maps->entries = RB_ROOT;
+	init_rwsem(&maps->lock);
+	maps->machine = machine;
+	maps->last_search_by_name = NULL;
+	maps->nr_maps = 0;
+	maps->maps_by_name = NULL;
+	refcount_set(&maps->refcnt, 1);
+}
+
+static void __maps__free_maps_by_name(struct maps *maps)
+{
+	/*
+	 * Free everything to try to do it from the rbtree in the next search
+	 */
+	zfree(&maps->maps_by_name);
+	maps->nr_maps_allocated = 0;
+}
+
+void maps__insert(struct maps *maps, struct map *map)
+{
+	down_write(&maps->lock);
+	__maps__insert(maps, map);
+	++maps->nr_maps;
+
+	if (map->dso && map->dso->kernel) {
+		struct kmap *kmap = map__kmap(map);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+
+
+	/*
+	 * If we already performed some search by name, then we need to add the just
+	 * inserted map and resort.
+	 */
+	if (maps->maps_by_name) {
+		if (maps->nr_maps > maps->nr_maps_allocated) {
+			int nr_allocate = maps->nr_maps * 2;
+			struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map));
+
+			if (maps_by_name == NULL) {
+				__maps__free_maps_by_name(maps);
+				up_write(&maps->lock);
+				return;
+			}
+
+			maps->maps_by_name = maps_by_name;
+			maps->nr_maps_allocated = nr_allocate;
+		}
+		maps->maps_by_name[maps->nr_maps - 1] = map;
+		__maps__sort_by_name(maps);
+	}
+	up_write(&maps->lock);
+}
+
+static void __maps__remove(struct maps *maps, struct map *map)
+{
+	rb_erase_init(&map->rb_node, &maps->entries);
+	map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	down_write(&maps->lock);
+	if (maps->last_search_by_name == map)
+		maps->last_search_by_name = NULL;
+
+	__maps__remove(maps, map);
+	--maps->nr_maps;
+	if (maps->maps_by_name)
+		__maps__free_maps_by_name(maps);
+	up_write(&maps->lock);
+}
+
+static void __maps__purge(struct maps *maps)
+{
+	struct map *pos, *next;
+
+	maps__for_each_entry_safe(maps, pos, next) {
+		rb_erase_init(&pos->rb_node,  &maps->entries);
+		map__put(pos);
+	}
+}
+
+static void maps__exit(struct maps *maps)
+{
+	down_write(&maps->lock);
+	__maps__purge(maps);
+	up_write(&maps->lock);
+}
+
+bool maps__empty(struct maps *maps)
+{
+	return !maps__first(maps);
+}
+
+struct maps *maps__new(struct machine *machine)
+{
+	struct maps *maps = zalloc(sizeof(*maps));
+
+	if (maps != NULL)
+		maps__init(maps, machine);
+
+	return maps;
+}
+
+void maps__delete(struct maps *maps)
+{
+	maps__exit(maps);
+	unwind__finish_access(maps);
+	free(maps);
+}
+
+void maps__put(struct maps *maps)
+{
+	if (maps && refcount_dec_and_test(&maps->refcnt))
+		maps__delete(maps);
+}
+
+struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
+{
+	struct map *map = maps__find(maps, addr);
+
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map) >= 0) {
+		if (mapp != NULL)
+			*mapp = map;
+		return map__find_symbol(map, map->map_ip(map, addr));
+	}
+
+	return NULL;
+}
+
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
+{
+	struct symbol *sym;
+	struct map *pos;
+
+	down_read(&maps->lock);
+
+	maps__for_each_entry(maps, pos) {
+		sym = map__find_symbol_by_name(pos, name);
+
+		if (sym == NULL)
+			continue;
+		if (!map__contains_symbol(pos, sym)) {
+			sym = NULL;
+			continue;
+		}
+		if (mapp != NULL)
+			*mapp = pos;
+		goto out;
+	}
+
+	sym = NULL;
+out:
+	up_read(&maps->lock);
+	return sym;
+}
+
+int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
+{
+	if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) {
+		if (maps == NULL)
+			return -1;
+		ams->ms.map = maps__find(maps, ams->addr);
+		if (ams->ms.map == NULL)
+			return -1;
+	}
+
+	ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr);
+	ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr);
+
+	return ams->ms.sym ? 0 : -1;
+}
+
+size_t maps__fprintf(struct maps *maps, FILE *fp)
+{
+	size_t printed = 0;
+	struct map *pos;
+
+	down_read(&maps->lock);
+
+	maps__for_each_entry(maps, pos) {
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 2) {
+			printed += dso__fprintf(pos->dso, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+
+	up_read(&maps->lock);
+
+	return printed;
+}
+
+int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+{
+	struct rb_root *root;
+	struct rb_node *next, *first;
+	int err = 0;
+
+	down_write(&maps->lock);
+
+	root = &maps->entries;
+
+	/*
+	 * Find first map where end > map->start.
+	 * Same as find_vma() in kernel.
+	 */
+	next = root->rb_node;
+	first = NULL;
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+
+		if (pos->end > map->start) {
+			first = next;
+			if (pos->start <= map->start)
+				break;
+			next = next->rb_left;
+		} else
+			next = next->rb_right;
+	}
+
+	next = first;
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		/*
+		 * Stop if current map starts after map->end.
+		 * Maps are ordered by start: next will not overlap for sure.
+		 */
+		if (pos->start >= map->end)
+			break;
+
+		if (verbose >= 2) {
+
+			if (use_browser) {
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
+					   map->dso->name);
+			} else {
+				fputs("overlapping maps:\n", fp);
+				map__fprintf(map, fp);
+				map__fprintf(pos, fp);
+			}
+		}
+
+		rb_erase_init(&pos->rb_node, root);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL) {
+				err = -ENOMEM;
+				goto put_map;
+			}
+
+			before->end = map->start;
+			__maps__insert(maps, before);
+			if (verbose >= 2 && !use_browser)
+				map__fprintf(before, fp);
+			map__put(before);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL) {
+				err = -ENOMEM;
+				goto put_map;
+			}
+
+			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
+			__maps__insert(maps, after);
+			if (verbose >= 2 && !use_browser)
+				map__fprintf(after, fp);
+			map__put(after);
+		}
+put_map:
+		map__put(pos);
+
+		if (err)
+			goto out;
+	}
+
+	err = 0;
+out:
+	up_write(&maps->lock);
+	return err;
+}
+
+/*
+ * XXX This should not really _copy_ te maps, but refcount them.
+ */
+int maps__clone(struct thread *thread, struct maps *parent)
+{
+	struct maps *maps = thread->maps;
+	int err;
+	struct map *map;
+
+	down_read(&parent->lock);
+
+	maps__for_each_entry(parent, map) {
+		struct map *new = map__clone(map);
+
+		if (new == NULL) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+
+		err = unwind__prepare_access(maps, new, NULL);
+		if (err)
+			goto out_unlock;
+
+		maps__insert(maps, new);
+		map__put(new);
+	}
+
+	err = 0;
+out_unlock:
+	up_read(&parent->lock);
+	return err;
+}
+
+static void __maps__insert(struct maps *maps, struct map *map)
+{
+	struct rb_node **p = &maps->entries.rb_node;
+	struct rb_node *parent = NULL;
+	const u64 ip = map->start;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color(&map->rb_node, &maps->entries);
+	map__get(map);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+	struct rb_node *p;
+	struct map *m;
+
+	down_read(&maps->lock);
+
+	p = maps->entries.rb_node;
+	while (p != NULL) {
+		m = rb_entry(p, struct map, rb_node);
+		if (ip < m->start)
+			p = p->rb_left;
+		else if (ip >= m->end)
+			p = p->rb_right;
+		else
+			goto out;
+	}
+
+	m = NULL;
+out:
+	up_read(&maps->lock);
+	return m;
+}
+
+struct map *maps__first(struct maps *maps)
+{
+	struct rb_node *first = rb_first(&maps->entries);
+
+	if (first)
+		return rb_entry(first, struct map, rb_node);
+	return NULL;
+}