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, 161 insertions, 3 deletions

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index e8613cbda331..ec43d364d0de 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -46,6 +46,12 @@
 
 #define MAX_TIMESTAMP (~0ULL)
 
+#define INTEL_PT_CFG_PASS_THRU	BIT_ULL(0)
+#define INTEL_PT_CFG_PWR_EVT_EN	BIT_ULL(4)
+#define INTEL_PT_CFG_BRANCH_EN	BIT_ULL(13)
+#define INTEL_PT_CFG_EVT_EN	BIT_ULL(31)
+#define INTEL_PT_CFG_TNT_DIS	BIT_ULL(55)
+
 struct range {
 	u64 start;
 	u64 end;
@@ -71,6 +77,7 @@ struct intel_pt {
 	bool mispred_all;
 	bool use_thread_stack;
 	bool callstack;
+	bool cap_event_trace;
 	unsigned int br_stack_sz;
 	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
@@ -115,6 +122,12 @@ struct intel_pt {
 	bool sample_pebs;
 	struct evsel *pebs_evsel;
 
+	u64 evt_sample_type;
+	u64 evt_id;
+
+	u64 iflag_chg_sample_type;
+	u64 iflag_chg_id;
+
 	u64 tsc_bit;
 	u64 mtc_bit;
 	u64 mtc_freq_bits;
@@ -953,12 +966,26 @@ static bool intel_pt_branch_enable(struct intel_pt *pt)
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
-		    (config & 1) && !(config & 0x2000))
+		    (config & INTEL_PT_CFG_PASS_THRU) &&
+		    !(config & INTEL_PT_CFG_BRANCH_EN))
 			return false;
 	}
 	return true;
 }
 
+static bool intel_pt_disabled_tnt(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+	u64 config;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
+		    config & INTEL_PT_CFG_TNT_DIS)
+			return true;
+	}
+	return false;
+}
+
 static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 {
 	struct evsel *evsel;
@@ -1214,6 +1241,10 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	params.first_timestamp = pt->first_timestamp;
 	params.max_loops = pt->max_loops;
 
+	/* Cannot walk code without TNT, so force 'quick' mode */
+	if (params.branch_enable && intel_pt_disabled_tnt(pt) && !params.quick)
+		params.quick = 1;
+
 	if (pt->filts.cnt > 0)
 		params.pgd_ip = intel_pt_pgd_ip;
 
@@ -1316,6 +1347,8 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 
 static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 {
+	struct intel_pt *pt = ptq->pt;
+
 	ptq->insn_len = 0;
 	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
 		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
@@ -1346,6 +1379,17 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
 	if (ptq->state->type & INTEL_PT_TRACE_END)
 		ptq->flags |= PERF_IP_FLAG_TRACE_END;
+
+	if (pt->cap_event_trace) {
+		if (ptq->state->type & INTEL_PT_IFLAG_CHG) {
+			if (!ptq->state->from_iflag)
+				ptq->flags |= PERF_IP_FLAG_INTR_DISABLE;
+			if (ptq->state->from_iflag != ptq->state->to_iflag)
+				ptq->flags |= PERF_IP_FLAG_INTR_TOGGLE;
+		} else if (!ptq->state->to_iflag) {
+			ptq->flags |= PERF_IP_FLAG_INTR_DISABLE;
+		}
+	}
 }
 
 static void intel_pt_setup_time_range(struct intel_pt *pt,
@@ -2160,6 +2204,78 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 	return err;
 }
 
+static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq)
+{
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+	struct {
+		struct perf_synth_intel_evt cfe;
+		struct perf_synth_intel_evd evd[INTEL_PT_MAX_EVDS];
+	} raw;
+	int i;
+
+	if (intel_pt_skip_event(pt))
+		return 0;
+
+	intel_pt_prep_p_sample(pt, ptq, event, &sample);
+
+	sample.id        = ptq->pt->evt_id;
+	sample.stream_id = ptq->pt->evt_id;
+
+	raw.cfe.type     = ptq->state->cfe_type;
+	raw.cfe.reserved = 0;
+	raw.cfe.ip       = !!(ptq->state->flags & INTEL_PT_FUP_IP);
+	raw.cfe.vector   = ptq->state->cfe_vector;
+	raw.cfe.evd_cnt  = ptq->state->evd_cnt;
+
+	for (i = 0; i < ptq->state->evd_cnt; i++) {
+		raw.evd[i].et       = 0;
+		raw.evd[i].evd_type = ptq->state->evd[i].type;
+		raw.evd[i].payload  = ptq->state->evd[i].payload;
+	}
+
+	sample.raw_size = perf_synth__raw_size(raw) +
+			  ptq->state->evd_cnt * sizeof(struct perf_synth_intel_evd);
+	sample.raw_data = perf_synth__raw_data(&raw);
+
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->evt_sample_type);
+}
+
+static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq)
+{
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+	struct perf_synth_intel_iflag_chg raw;
+
+	if (intel_pt_skip_event(pt))
+		return 0;
+
+	intel_pt_prep_p_sample(pt, ptq, event, &sample);
+
+	sample.id = ptq->pt->iflag_chg_id;
+	sample.stream_id = ptq->pt->iflag_chg_id;
+
+	raw.flags = 0;
+	raw.iflag = ptq->state->to_iflag;
+
+	if (ptq->state->type & INTEL_PT_BRANCH) {
+		raw.via_branch = 1;
+		raw.branch_ip = ptq->state->to_ip;
+	} else {
+		sample.addr = 0;
+	}
+	sample.flags = ptq->flags;
+
+	sample.raw_size = perf_synth__raw_size(raw);
+	sample.raw_data = perf_synth__raw_data(&raw);
+
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->iflag_chg_sample_type);
+}
+
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
@@ -2266,6 +2382,19 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
+	if (pt->synth_opts.intr_events) {
+		if (state->type & INTEL_PT_EVT) {
+			err = intel_pt_synth_events_sample(ptq);
+			if (err)
+				return err;
+		}
+		if (state->type & INTEL_PT_IFLAG_CHG) {
+			err = intel_pt_synth_iflag_chg_sample(ptq);
+			if (err)
+				return err;
+		}
+	}
+
 	if (pt->sample_pwr_events) {
 		if (state->type & INTEL_PT_PSB_EVT) {
 			err = intel_pt_synth_psb_sample(ptq);
@@ -3429,7 +3558,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		id += 1;
 	}
 
-	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) {
+	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & INTEL_PT_CFG_PWR_EVT_EN)) {
 		attr.config = PERF_SYNTH_INTEL_MWAIT;
 		err = intel_pt_synth_event(session, "mwait", &attr, id);
 		if (err)
@@ -3463,6 +3592,28 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		id += 1;
 	}
 
+	if (pt->synth_opts.intr_events && (evsel->core.attr.config & INTEL_PT_CFG_EVT_EN)) {
+		attr.config = PERF_SYNTH_INTEL_EVT;
+		err = intel_pt_synth_event(session, "evt", &attr, id);
+		if (err)
+			return err;
+		pt->evt_sample_type = attr.sample_type;
+		pt->evt_id = id;
+		intel_pt_set_event_name(evlist, id, "evt");
+		id += 1;
+	}
+
+	if (pt->synth_opts.intr_events && pt->cap_event_trace) {
+		attr.config = PERF_SYNTH_INTEL_IFLAG_CHG;
+		err = intel_pt_synth_event(session, "iflag", &attr, id);
+		if (err)
+			return err;
+		pt->iflag_chg_sample_type = attr.sample_type;
+		pt->iflag_chg_id = id;
+		intel_pt_set_event_name(evlist, id, "iflag");
+		id += 1;
+	}
+
 	return 0;
 }
 
@@ -3790,7 +3941,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	}
 
 	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
-	info_end = (void *)info + auxtrace_info->header.size;
+	info_end = (void *)auxtrace_info + auxtrace_info->header.size;
 
 	if (intel_pt_has(auxtrace_info, INTEL_PT_FILTER_STR_LEN)) {
 		size_t len;
@@ -3829,6 +3980,13 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		intel_pt_print_info_str("Filter string", pt->filter);
 	}
 
+	if ((void *)info < info_end) {
+		pt->cap_event_trace = *info++;
+		if (dump_trace)
+			fprintf(stdout, "  Cap Event Trace     %d\n",
+				pt->cap_event_trace);
+	}
+
 	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
 	if (pt->timeless_decoding && !pt->tc.time_mult)
 		pt->tc.time_mult = 1;