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, 21 insertions, 17 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 394550003693..b80048546451 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -89,7 +89,10 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	int err = -ENOMEM;
 
 	memset(machine, 0, sizeof(*machine));
-	maps__init(&machine->kmaps, machine);
+	machine->kmaps = maps__new(machine);
+	if (machine->kmaps == NULL)
+		return -ENOMEM;
+
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
@@ -108,7 +111,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
-		return -ENOMEM;
+		goto out;
 
 	if (machine__set_mmap_name(machine))
 		goto out;
@@ -131,6 +134,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 out:
 	if (err) {
+		zfree(&machine->kmaps);
 		zfree(&machine->root_dir);
 		zfree(&machine->mmap_name);
 	}
@@ -220,7 +224,7 @@ void machine__exit(struct machine *machine)
 		return;
 
 	machine__destroy_kernel_maps(machine);
-	maps__exit(&machine->kmaps);
+	maps__delete(machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
@@ -778,7 +782,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 					     struct perf_sample *sample __maybe_unused)
 {
 	struct symbol *sym;
-	struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
+	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 
 	if (!map) {
 		struct dso *dso = dso__new(event->ksymbol.name);
@@ -801,7 +805,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
-		maps__insert(&machine->kmaps, map);
+		maps__insert(machine__kernel_maps(machine), map);
 		map__put(map);
 		dso__set_loaded(dso);
 
@@ -827,12 +831,12 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 	struct symbol *sym;
 	struct map *map;
 
-	map = maps__find(&machine->kmaps, event->ksymbol.addr);
+	map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 	if (!map)
 		return 0;
 
 	if (map != machine->vmlinux_map)
-		maps__remove(&machine->kmaps, map);
+		maps__remove(machine__kernel_maps(machine), map);
 	else {
 		sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
 		if (sym)
@@ -858,7 +862,7 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
 int machine__process_text_poke(struct machine *machine, union perf_event *event,
 			       struct perf_sample *sample __maybe_unused)
 {
-	struct map *map = maps__find(&machine->kmaps, event->text_poke.addr);
+	struct map *map = maps__find(machine__kernel_maps(machine), event->text_poke.addr);
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (dump_trace)
@@ -914,7 +918,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start
 	if (map == NULL)
 		goto out;
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 
 	/* Put the map here because maps__insert already got it */
 	map__put(map);
@@ -1100,7 +1104,7 @@ int machine__create_extra_kernel_map(struct machine *machine,
 
 	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 
 	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
 		  kmap->name, map->start, map->end);
@@ -1145,7 +1149,7 @@ static u64 find_entry_trampoline(struct dso *dso)
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel)
 {
-	struct maps *kmaps = &machine->kmaps;
+	struct maps *kmaps = machine__kernel_maps(machine);
 	int nr_cpus_avail, cpu;
 	bool found = false;
 	struct map *map;
@@ -1215,7 +1219,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		return -1;
 
 	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
-	maps__insert(&machine->kmaps, machine->vmlinux_map);
+	maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
 	return 0;
 }
 
@@ -1228,7 +1232,7 @@ void machine__destroy_kernel_maps(struct machine *machine)
 		return;
 
 	kmap = map__kmap(map);
-	maps__remove(&machine->kmaps, map);
+	maps__remove(machine__kernel_maps(machine), map);
 	if (kmap && kmap->ref_reloc_sym) {
 		zfree((char **)&kmap->ref_reloc_sym->name);
 		zfree(&kmap->ref_reloc_sym);
@@ -1323,7 +1327,7 @@ int machine__load_kallsyms(struct machine *machine, const char *filename)
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		maps__fixup_end(&machine->kmaps);
+		maps__fixup_end(machine__kernel_maps(machine));
 	}
 
 	return ret;
@@ -1471,7 +1475,7 @@ static int machine__set_modules_path(struct machine *machine)
 		 machine->root_dir, version);
 	free(version);
 
-	return maps__set_modules_path_dir(&machine->kmaps, modules_path, 0);
+	return maps__set_modules_path_dir(machine__kernel_maps(machine), modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
 				u64 *size __maybe_unused,
@@ -1544,11 +1548,11 @@ static void machine__update_kernel_mmap(struct machine *machine,
 	struct map *map = machine__kernel_map(machine);
 
 	map__get(map);
-	maps__remove(&machine->kmaps, map);
+	maps__remove(machine__kernel_maps(machine), map);
 
 	machine__set_kernel_mmap(machine, start, end);
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 	map__put(map);
 }