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
  ...

6 files changed, 40 insertions, 9 deletions

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2e8b2c4365a0..cbc555245959 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -510,6 +510,9 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
 	if (config_opts & BIT(ETM_OPT_CTXTID2))
 		config |= BIT(ETM4_CFG_BIT_VMID) |
 			  BIT(ETM4_CFG_BIT_VMID_OPT);
+	if (config_opts & BIT(ETM_OPT_BRANCH_BROADCAST))
+		config |= BIT(ETM4_CFG_BIT_BB);
+
 	return config;
 }
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 2100d46ccf5e..5860bbaea95a 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -158,7 +158,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 				return -EINVAL;
 			}
 			evsel->core.attr.freq = 0;
-			evsel->core.attr.sample_period = 1;
+			evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period;
 			arm_spe_evsel = evsel;
 			opts->full_auxtrace = true;
 		}
diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
index 2fc882ab24c1..42237656f453 100644
--- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
+++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
@@ -17,7 +17,7 @@
  * @new_ctx: expected new packet context
  * @ctx_unchanged: the packet context must not change
  */
-struct test_data {
+static struct test_data {
 	int len;
 	u8 bytes[INTEL_PT_PKT_MAX_SZ];
 	enum intel_pt_pkt_ctx ctx;
@@ -70,8 +70,11 @@ struct test_data {
 	{8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0xC0A08060403}, 0, 0 },
 	/* Mode Exec Packet */
 	{2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 },
-	{2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 0, 64}, 0, 0 },
-	{2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 0, 32}, 0, 0 },
+	{2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 1, 64}, 0, 0 },
+	{2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 2, 32}, 0, 0 },
+	{2, {0x99, 0x04}, 0, {INTEL_PT_MODE_EXEC, 4, 16}, 0, 0 },
+	{2, {0x99, 0x05}, 0, {INTEL_PT_MODE_EXEC, 5, 64}, 0, 0 },
+	{2, {0x99, 0x06}, 0, {INTEL_PT_MODE_EXEC, 6, 32}, 0, 0 },
 	/* Mode TSX Packet */
 	{2, {0x99, 0x20}, 0, {INTEL_PT_MODE_TSX, 0, 0}, 0, 0 },
 	{2, {0x99, 0x21}, 0, {INTEL_PT_MODE_TSX, 0, 1}, 0, 0 },
@@ -166,6 +169,14 @@ struct test_data {
 	{2, {0x02, 0xb3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
 	{2, {0x02, 0x33}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
 	{2, {0x02, 0xb3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
+	/* Control Flow Event Packet */
+	{4, {0x02, 0x13, 0x01, 0x03}, 0, {INTEL_PT_CFE, 1, 3}, 0, 0 },
+	{4, {0x02, 0x13, 0x81, 0x03}, 0, {INTEL_PT_CFE_IP, 1, 3}, 0, 0 },
+	{4, {0x02, 0x13, 0x1f, 0x00}, 0, {INTEL_PT_CFE, 0x1f, 0}, 0, 0 },
+	{4, {0x02, 0x13, 0x9f, 0xff}, 0, {INTEL_PT_CFE_IP, 0x1f, 0xff}, 0, 0 },
+	/*  */
+	{11, {0x02, 0x53, 0x09, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_EVD, 0x09, 0x7060504030201}, 0, 0 },
+	{11, {0x02, 0x53, 0x3f, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_EVD, 0x3f, 0x8070605040302}, 0, 0 },
 	/* Terminator */
 	{0, {0}, 0, {0, 0, 0}, 0, 0 },
 };
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index 9b31734ee968..e670f3547581 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -18,7 +18,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
 {
 	int rc = 0;
 	struct map *pos;
-	struct maps *kmaps = &machine->kmaps;
+	struct maps *kmaps = machine__kernel_maps(machine);
 	union perf_event *event = zalloc(sizeof(event->mmap) +
 					 machine->id_hdr_size);
 
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 8d9b55959256..cfc208d71f00 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -20,17 +20,27 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
 
 struct evsel *arch_evlist__leader(struct list_head *list)
 {
-	struct evsel *evsel, *first;
+	struct evsel *evsel, *first, *slots = NULL;
+	bool has_topdown = false;
 
 	first = list_first_entry(list, struct evsel, core.node);
 
 	if (!pmu_have_event("cpu", "slots"))
 		return first;
 
+	/* If there is a slots event and a topdown event then the slots event comes first. */
 	__evlist__for_each_entry(list, evsel) {
-		if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
-			evsel->name && strcasestr(evsel->name, "slots"))
-			return evsel;
+		if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
+			if (strcasestr(evsel->name, "slots")) {
+				slots = evsel;
+				if (slots == first)
+					return first;
+			}
+			if (!strncasecmp(evsel->name, "topdown", 7))
+				has_topdown = true;
+			if (slots && has_topdown)
+				return slots;
+		}
 	}
 	return first;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 6df0dc00d73a..8c31578d6f4a 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -306,6 +306,7 @@ intel_pt_info_priv_size(struct auxtrace_record *itr, struct evlist *evlist)
 
 	ptr->priv_size = (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64)) +
 			 intel_pt_filter_bytes(filter);
+	ptr->priv_size += sizeof(u64); /* Cap Event Trace */
 
 	return ptr->priv_size;
 }
@@ -335,6 +336,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	unsigned long max_non_turbo_ratio;
 	size_t filter_str_len;
 	const char *filter;
+	int event_trace;
 	__u64 *info;
 	int err;
 
@@ -357,6 +359,9 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	if (perf_pmu__scan_file(intel_pt_pmu, "max_nonturbo_ratio",
 				"%lu", &max_non_turbo_ratio) != 1)
 		max_non_turbo_ratio = 0;
+	if (perf_pmu__scan_file(intel_pt_pmu, "caps/event_trace",
+				"%d", &event_trace) != 1)
+		event_trace = 0;
 
 	filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu);
 	filter_str_len = filter ? strlen(filter) : 0;
@@ -407,6 +412,8 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 		info += len >> 3;
 	}
 
+	*info++ = event_trace;
+
 	return 0;
 }