Merge tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "perf annotate:
   - Add riscv64 support.
   - Add fusion logic for AMD microarchs.

  perf record:
   - Add an option to control the synthesizing behavior:
       --synth <no|all|task|mmap|cgroup>

  core:
   - Allow controlling synthesizing PERF_RECORD_ metadata events during
     record.
   - perf.data reader prep work for multithreaded processing.
   - Fix missing exclude_{host,guest} setting in PMUs that don't support
     it and that were causing the feature detection code to disable it
     for all events, even the ones in PMUs that support it.
   - Fix the default use of precise events on AMD, that were always
     falling back to non-precise because perf_event_attr.exclude_guest=1
     was set and IBS does not have filtering capability, refusing
     precise + exclude_guest.
   - Add bitfield_swap() to handle branch_stack endian issue.

  perf script:
   - Show binary offsets for userspace addresses in callchains.
   - Support instruction latency via new "ins_lat" selectable field.
   - Add dlfilter-show-cycles

  perf inject:
   - Add vmlinux and ignore-vmlinux arguments, similar to other tools.

  perf list:
   - Display PMU prefix for partially supported hybrid cache events.
   - Display hybrid PMU events with cpu type.

  perf stat:
   - Improve metrics documentation of data structures.
   - Fix memory leaks in the metric code.
   - Use NAN for missing event IDs.
   - Don't compute unused events.
   - Fix memory leak on error path.
   - Encode and use metric-id as a metric qualifier.
   - Allow metrics with no events.
   - Avoid events for an 'if' constant result.
   - Only add a referenced metric once.
   - Simplify metric_refs calculation.
   - Allow modifiers on metrics.

  perf test:
   - Add workload test of metric and metric groups.
   - Workload test of all PMUs.
   - vmlinux-kallsyms: Ignore hidden symbols.
   - Add pmu-event test for event described as "config=".
   - Verify more event members in pmu-events test.
   - Add endian test for struct branch_flags on the sample-parsing test.
   - Improve temp file cleanup in several tests.

  perf daemon:
   - Address MSAN warnings on send_cmd().

  perf kmem:
   - Improve man page for record options

  perf srcline:
   - Use long-running addr2line per DSO, greatly speeding up the
     'srcline' sort order.

  perf symbols:
   - Ignore $a/$d symbols for ARM modules.
   - Fix /proc/kcore access on 32 bit systems.

  Kernel UAPI copies:
   - Update copy of linux/socket.h with the kernel sources, no change in
     tooling output.

  libbpf:
   - Pull in bpf_program__get_prog_info_linear() from libbpf, too much
     specific to perf.
   - Deprecate bpf_map__resize() in favor of bpf_map_set_max_entries()
   - Install libbpf headers locally when building.
   - Bump minimum LLVM C++ std to GNU++14.

  libperf:
   - Use binary search in perf_cpu_map__idx() as array are sorted.

  libtracefs:
   - Enable libtracefs dynamic linking.

  libtraceevent:
   - Increase logging when verbose.

  Arch specific:

   * PowerPC:
      - Add support to expose instruction and data address registers as
        part of extended regs.

  Vendor events:

   * JSON parser:
      - Support ConfigCode to set the config= in PMUs
      - Make the JSON parser more conformant when in strict mode.

   * All JSON files:
      - Fix all remaining invalid JSON files.

   * ARM:
      - Syntax corrections in Neoverse N1 json.
      - Categorise the Neoverse V1 counters.
      - Add new armv8 PMU events.
      - Revise hip08 uncore events.

  Hardware tracing:

   * auxtrace:
      - Add missing Z option to ITRACE_HELP.
      - Add itrace A option to approximate IPC.
      - Add itrace d+o option to direct debug log to stdout.

   * Intel PT:
      - Add support for PERF_RECORD_AUX_OUTPUT_HW_ID
      - Support itrace A option to approximate IPC
      - Support itrace d+o option to direct debug log to stdout"

* tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (120 commits)
  perf build: Install libbpf headers locally when building
  perf MANIFEST: Add bpftool files to allow building with BUILD_BPF_SKEL=1
  perf metric: Fix memory leaks
  perf parse-event: Add init and exit to parse_event_error
  perf parse-events: Rename parse_events_error functions
  perf stat: Fix memory leak on error path
  perf tools: Use __BYTE_ORDER__
  perf inject: Add vmlinux and ignore-vmlinux arguments
  perf tools: Check vmlinux/kallsyms arguments in all tools
  perf tools: Refactor out kernel symbol argument sanity checking
  perf symbols: Ignore $a/$d symbols for ARM modules
  perf evsel: Don't set exclude_guest by default
  perf evsel: Fix missing exclude_{host,guest} setting
  perf bpf: Add missing free to bpf_event__print_bpf_prog_info()
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf clang: Fixes for more recent LLVM/clang
  tools: Bump minimum LLVM C++ std to GNU++14
  perf bpf: Pull in bpf_program__get_prog_info_linear()
  Revert "perf bench futex: Add support for 32-bit systems with 64-bit time_t"
  perf test sample-parsing: Add endian test for struct branch_flags
  ...

1 files changed, 38 insertions, 5 deletions

diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 8fd8a4ef97da1..c83a115141291 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -13,6 +13,7 @@
 #include "evsel.h"
 #include "debug.h"
 #include "util/synthetic-events.h"
+#include "util/trace-event.h"
 
 #include "tests.h"
 
@@ -30,9 +31,18 @@
 	}						\
 } while (0)
 
+/*
+ * Hardcode the expected values for branch_entry flags.
+ * These are based on the input value (213) specified
+ * in branch_stack variable.
+ */
+#define BS_EXPECTED_BE	0xa00d000000000000
+#define BS_EXPECTED_LE	0xd5000000
+#define FLAG(s)	s->branch_stack->entries[i].flags
+
 static bool samples_same(const struct perf_sample *s1,
 			 const struct perf_sample *s2,
-			 u64 type, u64 read_format)
+			 u64 type, u64 read_format, bool needs_swap)
 {
 	size_t i;
 
@@ -100,8 +110,14 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		COMP(branch_stack->nr);
 		COMP(branch_stack->hw_idx);
-		for (i = 0; i < s1->branch_stack->nr; i++)
-			MCOMP(branch_stack->entries[i]);
+		for (i = 0; i < s1->branch_stack->nr; i++) {
+			if (needs_swap)
+				return ((tep_is_bigendian()) ?
+					(FLAG(s2).value == BS_EXPECTED_BE) :
+					(FLAG(s2).value == BS_EXPECTED_LE));
+			else
+				MCOMP(branch_stack->entries[i]);
+		}
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
@@ -248,7 +264,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		},
 	};
 	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
-	struct perf_sample sample_out;
+	struct perf_sample sample_out, sample_out_endian;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
 
@@ -313,12 +329,29 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		goto out_free;
 	}
 
-	if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
+	if (!samples_same(&sample, &sample_out, sample_type, read_format, evsel.needs_swap)) {
 		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
 			 sample_type);
 		goto out_free;
 	}
 
+	if (sample_type == PERF_SAMPLE_BRANCH_STACK) {
+		evsel.needs_swap = true;
+		evsel.sample_size = __evsel__sample_size(sample_type);
+		err = evsel__parse_sample(&evsel, event, &sample_out_endian);
+		if (err) {
+			pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+				 "evsel__parse_sample", sample_type, err);
+			goto out_free;
+		}
+
+		if (!samples_same(&sample, &sample_out_endian, sample_type, read_format, evsel.needs_swap)) {
+			pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+				 sample_type);
+			goto out_free;
+		}
+	}
+
 	ret = 0;
 out_free:
 	free(event);