Merge tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next

Pull perf tools updates from Namhyung Kim:
 "Internal cleanup:

   - Refactor PMU data management to handle hybrid systems in a generic
     way.

     Do more work in the lexer so that legacy event types parse more
     easily. A side-effect of this is that if a PMU is specified,
     scanning sysfs is avoided improving start-up time.

   - Fix hybrid metrics, for example, the TopdownL1 works for both
     performance and efficiency cores on Intel machines. To support
     this, sort and regroup events after parsing.

   - Add reference count checking for the 'thread' data structure.

   - Lots of fixes for memory leaks in various places thanks to the ASAN
     and Ian's refcount checker.

   - Reduce the binary size by replacing static variables with local or
     dynamically allocated memory.

   - Introduce shared_mutex for annotate data to reduce memory
     footprint.

   - Make filesystem access library functions more thread safe.

  Test:

   - Organize cpu_map tests into a single suite.

   - Add metric value validation test to check if the values are within
     correct value ranges.

   - Add perf stat stdio output test to check if event and metric names
     match.

   - Add perf data converter JSON output test.

   - Fix a lot of issues reported by shellcheck(1). This is a
     preparation to enable shellcheck by default.

   - Make the large x86 new instructions test optional at build time
     using EXTRA_TESTS=1.

   - Add a test for libpfm4 events.

  perf script:

   - Add 'dsoff' outpuf field to display offset from the DSO.

      $ perf script -F comm,pid,event,ip,dsoff
         ls 2695501 cycles:      152cc73ef4b5 (/usr/lib/x86_64-linux-gnu/ld-2.31.so+0x1c4b5)
         ls 2695501 cycles:  ffffffff99045b3e ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968e107 ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffffc1f54afb ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968382f ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff99e00094 ([kernel.kallsyms])
         ls 2695501 cycles:      152cc718a8d0 (/usr/lib/x86_64-linux-gnu/libselinux.so.1+0x68d0)
         ls 2695501 cycles:  ffffffff992a6db0 ([kernel.kallsyms])

   - Adjust width for large PID/TID values.

  perf report:

   - Robustify reading addr2line output for srcline by checking sentinel
     output before the actual data and by using timeout of 1 second.

   - Allow config terms (like 'name=ABC') with breakpoint events.

      $ perf record -e mem:0x55feb98dd169:x/name=breakpoint/ -p 19646 -- sleep 1

  perf annotate:

   - Handle x86 instruction suffix like 'l' in 'movl' generally.

   - Parse instruction operands properly even with a whitespace. This is
     needed for llvm-objdump output.

   - Support RISC-V binutils lookup using the triplet prefixes.

   - Add '<' and '>' key to navigate to prev/next symbols in TUI.

   - Fix instruction association and parsing for LoongArch.

  perf stat:

   - Add --per-cache aggregation option, optionally specify a cache
     level like `--per-cache=L2`.

      $ sudo perf stat --per-cache -a -e ls_dmnd_fills_from_sys.ext_cache_remote --\
        taskset -c 0-15,64-79,128-143,192-207\
        perf bench sched messaging -p -t -l 100000 -g 8

        # Running 'sched/messaging' benchmark:
        # 20 sender and receiver threads per group
        # 8 groups == 320 threads run

        Total time: 7.648 [sec]

        Performance counter stats for 'system wide':

        S0-D0-L3-ID0             16         17,145,912      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID8             16         14,977,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID16            16            262,539      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID24            16              3,140      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID32            16             27,403      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID40            16             17,026      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID48            16              7,292      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID56            16              2,464      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID64            16         22,489,306      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID72            16         21,455,257      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID80            16             11,619      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID88            16             30,978      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID96            16             37,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID104           16             13,594      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID112           16             10,164      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID120           16             11,259      ls_dmnd_fills_from_sys.ext_cache_remote

              7.779171484 seconds time elapsed

   - Change default (no event/metric) formatting for default metrics so
     that events are hidden and the metric and group appear.

       Performance counter stats for 'ls /':

                    1.85 msec task-clock                       #    0.594 CPUs utilized
                       0      context-switches                 #    0.000 /sec
                       0      cpu-migrations                   #    0.000 /sec
                      97      page-faults                      #   52.517 K/sec
               2,187,173      cycles                           #    1.184 GHz
               2,474,459      instructions                     #    1.13  insn per cycle
                 531,584      branches                         #  287.805 M/sec
                  13,626      branch-misses                    #    2.56% of all branches
                              TopdownL1                 #     23.5 %  tma_backend_bound
                                                        #     11.5 %  tma_bad_speculation
                                                        #     39.1 %  tma_frontend_bound
                                                        #     25.9 %  tma_retiring

   - Allow --cputype option to have any PMU name (not just hybrid).

   - Fix output value not to added when it runs multiple times with -r
     option.

  perf list:

   - Show metricgroup description from JSON file called
     metricgroups.json.

   - Allow 'pfm' argument to list only libpfm4 events and check each
     event is supported before showing it.

  JSON vendor events:

   - Avoid event grouping using "NO_GROUP_EVENTS" constraints. The
     topdown events are correctly grouped even if no group exists.

   - Add "Default" metric group to print it in the default output. And
     use "DefaultMetricgroupName" to indicate the real metric group
     name.

   - Add AmpereOne core PMU events.

  Misc:

   - Define man page date correctly.

   - Track exception level properly on ARM CoreSight ETM.

   - Allow anonymous struct, union or enum when retrieving type names
     from DWARF.

   - Fix incorrect filename when calling `perf inject --jit`.

   - Handle PLT size correctly on LoongArch"

* tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (269 commits)
  perf test: Skip metrics w/o event name in stat STD output linter
  perf test: Reorder event name checks in stat STD output linter
  perf pmu: Remove a hard coded cpu PMU assumption
  perf pmus: Add notion of default PMU for JSON events
  perf unwind: Fix map reference counts
  perf test: Set PERF_EXEC_PATH for script execution
  perf script: Initialize buffer for regs_map()
  perf tests: Fix test_arm_callgraph_fp variable expansion
  perf symbol: Add LoongArch case in get_plt_sizes()
  perf test: Remove x permission from lib/stat_output.sh
  perf test: Rerun failed metrics with longer workload
  perf test: Add skip list for metrics known would fail
  perf test: Add metric value validation test
  perf jit: Fix incorrect file name in DWARF line table
  perf annotate: Fix instruction association and parsing for LoongArch
  perf annotation: Switch lock from a mutex to a sharded_mutex
  perf sharded_mutex: Introduce sharded_mutex
  tools: Fix incorrect calculation of object size by sizeof
  perf subcmd: Fix missing check for return value of malloc() in add_cmdname()
  perf parse-events: Remove unneeded semicolon
  ...

22 files changed, 430 insertions, 144 deletions

diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 305872692bfd..5f4ac4fc7fcf 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -1,46 +1,37 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * x86 instruction nmemonic table to parse disasm lines for annotate.
+ * This table is searched twice - one for exact match and another for
+ * match without a size suffix (b, w, l, q) in case of AT&T syntax.
+ *
+ * So this table should not have entries with the suffix unless it's
+ * a complete different instruction than ones without the suffix.
+ */
 static struct ins x86__instructions[] = {
 	{ .name = "adc",	.ops = &mov_ops,  },
-	{ .name = "adcb",	.ops = &mov_ops,  },
-	{ .name = "adcl",	.ops = &mov_ops,  },
 	{ .name = "add",	.ops = &mov_ops,  },
-	{ .name = "addl",	.ops = &mov_ops,  },
-	{ .name = "addq",	.ops = &mov_ops,  },
 	{ .name = "addsd",	.ops = &mov_ops,  },
-	{ .name = "addw",	.ops = &mov_ops,  },
 	{ .name = "and",	.ops = &mov_ops,  },
-	{ .name = "andb",	.ops = &mov_ops,  },
-	{ .name = "andl",	.ops = &mov_ops,  },
 	{ .name = "andpd",	.ops = &mov_ops,  },
 	{ .name = "andps",	.ops = &mov_ops,  },
-	{ .name = "andq",	.ops = &mov_ops,  },
-	{ .name = "andw",	.ops = &mov_ops,  },
 	{ .name = "bsr",	.ops = &mov_ops,  },
 	{ .name = "bt",		.ops = &mov_ops,  },
 	{ .name = "btr",	.ops = &mov_ops,  },
 	{ .name = "bts",	.ops = &mov_ops,  },
-	{ .name = "btsq",	.ops = &mov_ops,  },
 	{ .name = "call",	.ops = &call_ops, },
-	{ .name = "callq",	.ops = &call_ops, },
 	{ .name = "cmovbe",	.ops = &mov_ops,  },
 	{ .name = "cmove",	.ops = &mov_ops,  },
 	{ .name = "cmovae",	.ops = &mov_ops,  },
 	{ .name = "cmp",	.ops = &mov_ops,  },
-	{ .name = "cmpb",	.ops = &mov_ops,  },
-	{ .name = "cmpl",	.ops = &mov_ops,  },
-	{ .name = "cmpq",	.ops = &mov_ops,  },
-	{ .name = "cmpw",	.ops = &mov_ops,  },
 	{ .name = "cmpxch",	.ops = &mov_ops,  },
 	{ .name = "cmpxchg",	.ops = &mov_ops,  },
 	{ .name = "cs",		.ops = &mov_ops,  },
 	{ .name = "dec",	.ops = &dec_ops,  },
-	{ .name = "decl",	.ops = &dec_ops,  },
 	{ .name = "divsd",	.ops = &mov_ops,  },
 	{ .name = "divss",	.ops = &mov_ops,  },
 	{ .name = "gs",		.ops = &mov_ops,  },
 	{ .name = "imul",	.ops = &mov_ops,  },
 	{ .name = "inc",	.ops = &dec_ops,  },
-	{ .name = "incl",	.ops = &dec_ops,  },
 	{ .name = "ja",		.ops = &jump_ops, },
 	{ .name = "jae",	.ops = &jump_ops, },
 	{ .name = "jb",		.ops = &jump_ops, },
@@ -54,7 +45,6 @@ static struct ins x86__instructions[] = {
 	{ .name = "jl",		.ops = &jump_ops, },
 	{ .name = "jle",	.ops = &jump_ops, },
 	{ .name = "jmp",	.ops = &jump_ops, },
-	{ .name = "jmpq",	.ops = &jump_ops, },
 	{ .name = "jna",	.ops = &jump_ops, },
 	{ .name = "jnae",	.ops = &jump_ops, },
 	{ .name = "jnb",	.ops = &jump_ops, },
@@ -81,48 +71,32 @@ static struct ins x86__instructions[] = {
 	{ .name = "mov",	.ops = &mov_ops,  },
 	{ .name = "movapd",	.ops = &mov_ops,  },
 	{ .name = "movaps",	.ops = &mov_ops,  },
-	{ .name = "movb",	.ops = &mov_ops,  },
 	{ .name = "movdqa",	.ops = &mov_ops,  },
 	{ .name = "movdqu",	.ops = &mov_ops,  },
-	{ .name = "movl",	.ops = &mov_ops,  },
-	{ .name = "movq",	.ops = &mov_ops,  },
 	{ .name = "movsd",	.ops = &mov_ops,  },
 	{ .name = "movslq",	.ops = &mov_ops,  },
 	{ .name = "movss",	.ops = &mov_ops,  },
 	{ .name = "movupd",	.ops = &mov_ops,  },
 	{ .name = "movups",	.ops = &mov_ops,  },
-	{ .name = "movw",	.ops = &mov_ops,  },
 	{ .name = "movzbl",	.ops = &mov_ops,  },
 	{ .name = "movzwl",	.ops = &mov_ops,  },
 	{ .name = "mulsd",	.ops = &mov_ops,  },
 	{ .name = "mulss",	.ops = &mov_ops,  },
 	{ .name = "nop",	.ops = &nop_ops,  },
-	{ .name = "nopl",	.ops = &nop_ops,  },
-	{ .name = "nopw",	.ops = &nop_ops,  },
 	{ .name = "or",		.ops = &mov_ops,  },
-	{ .name = "orb",	.ops = &mov_ops,  },
-	{ .name = "orl",	.ops = &mov_ops,  },
 	{ .name = "orps",	.ops = &mov_ops,  },
-	{ .name = "orq",	.ops = &mov_ops,  },
 	{ .name = "pand",	.ops = &mov_ops,  },
 	{ .name = "paddq",	.ops = &mov_ops,  },
 	{ .name = "pcmpeqb",	.ops = &mov_ops,  },
 	{ .name = "por",	.ops = &mov_ops,  },
-	{ .name = "rclb",	.ops = &mov_ops,  },
-	{ .name = "rcll",	.ops = &mov_ops,  },
+	{ .name = "rcl",	.ops = &mov_ops,  },
 	{ .name = "ret",	.ops = &ret_ops,  },
-	{ .name = "retq",	.ops = &ret_ops,  },
 	{ .name = "sbb",	.ops = &mov_ops,  },
-	{ .name = "sbbl",	.ops = &mov_ops,  },
 	{ .name = "sete",	.ops = &mov_ops,  },
 	{ .name = "sub",	.ops = &mov_ops,  },
-	{ .name = "subl",	.ops = &mov_ops,  },
-	{ .name = "subq",	.ops = &mov_ops,  },
 	{ .name = "subsd",	.ops = &mov_ops,  },
-	{ .name = "subw",	.ops = &mov_ops,  },
 	{ .name = "test",	.ops = &mov_ops,  },
-	{ .name = "testb",	.ops = &mov_ops,  },
-	{ .name = "testl",	.ops = &mov_ops,  },
+	{ .name = "tzcnt",	.ops = &mov_ops,  },
 	{ .name = "ucomisd",	.ops = &mov_ops,  },
 	{ .name = "ucomiss",	.ops = &mov_ops,  },
 	{ .name = "vaddsd",	.ops = &mov_ops,  },
@@ -135,11 +109,9 @@ static struct ins x86__instructions[] = {
 	{ .name = "vsubsd",	.ops = &mov_ops,  },
 	{ .name = "vucomisd",	.ops = &mov_ops,  },
 	{ .name = "xadd",	.ops = &mov_ops,  },
-	{ .name = "xbeginl",	.ops = &jump_ops, },
-	{ .name = "xbeginq",	.ops = &jump_ops, },
+	{ .name = "xbegin",	.ops = &jump_ops, },
 	{ .name = "xchg",	.ops = &mov_ops,  },
 	{ .name = "xor",	.ops = &mov_ops, },
-	{ .name = "xorb",	.ops = &mov_ops, },
 	{ .name = "xorpd",	.ops = &mov_ops, },
 	{ .name = "xorps",	.ops = &mov_ops, },
 };
diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
index 029a72c20b19..fa526a993845 100755
--- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
+++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
@@ -18,7 +18,7 @@ emit() {
     syscall_macro "$nr" "$entry"
 }
 
-echo "static const char *syscalltbl_${arch}[] = {"
+echo "static const char *const syscalltbl_${arch}[] = {"
 
 sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX)
 grep '^[0-9]' "$in" | sort -n > $sorted_table
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 93d3b8877baa..c0421a26b875 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -6,12 +6,15 @@ struct test_suite;
 
 /* Tests */
 int test__rdpmc(struct test_suite *test, int subtest);
+#ifdef HAVE_EXTRA_TESTS
 int test__insn_x86(struct test_suite *test, int subtest);
+#endif
 int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest);
 int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest);
 int test__bp_modify(struct test_suite *test, int subtest);
 int test__x86_sample_parsing(struct test_suite *test, int subtest);
 int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest);
+int test__hybrid(struct test_suite *test, int subtest);
 
 extern struct test_suite *arch_tests[];
 
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index fd02d8181718..b87f46e5feea 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -3,6 +3,10 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
 perf-y += sample-parsing.o
-perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-test.o
+perf-y += hybrid.o
+perf-$(CONFIG_AUXTRACE) += intel-pt-test.o
+ifeq ($(CONFIG_EXTRA_TESTS),y)
+perf-$(CONFIG_AUXTRACE) += insn-x86.o
+endif
 perf-$(CONFIG_X86_64) += bp-modify.o
 perf-y += amd-ibs-via-core-pmu.o
diff --git a/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c
index 2902798ca5c1..78b1902f6f59 100644
--- a/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c
+++ b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c
@@ -44,10 +44,7 @@ int test__amd_ibs_via_core_pmu(struct test_suite *test __maybe_unused,
 	int ret = TEST_OK;
 	int fd, i;
 
-	if (list_empty(&pmus))
-		perf_pmu__scan(NULL);
-
-	ibs_pmu = perf_pmu__find("ibs_op");
+	ibs_pmu = perf_pmus__find("ibs_op");
 	if (!ibs_pmu)
 		return TEST_SKIP;
 
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index b5c85ab8d92e..a216a5d172ed 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -4,7 +4,9 @@
 #include "arch-tests.h"
 
 #ifdef HAVE_AUXTRACE_SUPPORT
+#ifdef HAVE_EXTRA_TESTS
 DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86);
+#endif
 
 static struct test_case intel_pt_tests[] = {
 	TEST_CASE("Intel PT packet decoder", intel_pt_pkt_decoder),
@@ -23,13 +25,24 @@ DEFINE_SUITE("x86 bp modify", bp_modify);
 #endif
 DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing);
 DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu);
+static struct test_case hybrid_tests[] = {
+	TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__hybrid = {
+	.desc = "x86 hybrid",
+	.test_cases = hybrid_tests,
+};
 
 struct test_suite *arch_tests[] = {
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	&suite__dwarf_unwind,
 #endif
 #ifdef HAVE_AUXTRACE_SUPPORT
+#ifdef HAVE_EXTRA_TESTS
 	&suite__insn_x86,
+#endif
 	&suite__intel_pt,
 #endif
 #if defined(__x86_64__)
@@ -37,5 +50,6 @@ struct test_suite *arch_tests[] = {
 #endif
 	&suite__x86_sample_parsing,
 	&suite__amd_ibs_via_core_pmu,
+	&suite__hybrid,
 	NULL,
 };
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 497593be80f2..5bfec3345d59 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_X86_SP];
 
-	map = maps__find(thread->maps, (u64)sp);
+	map = maps__find(thread__maps(thread), (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c
new file mode 100644
index 000000000000..eb152770f148
--- /dev/null
+++ b/tools/perf/arch/x86/tests/hybrid.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arch-tests.h"
+#include "debug.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "tests/tests.h"
+
+static bool test_config(const struct evsel *evsel, __u64 expected_config)
+{
+	return (evsel->core.attr.config & PERF_HW_EVENT_MASK) == expected_config;
+}
+
+static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_config)
+{
+	return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config;
+}
+
+static bool test_hybrid_type(const struct evsel *evsel, __u64 expected_config)
+{
+	return (evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT) == expected_config;
+}
+
+static int test__hybrid_hw_event_with_pmu(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	return TEST_OK;
+}
+
+static int test__hybrid_hw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_sw_hw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_hw_sw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_group_modifier1(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
+	return TEST_OK;
+}
+
+static int test__hybrid_raw1(struct evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	perf_evlist__for_each_evsel(&evlist->core, evsel) {
+		struct perf_pmu *pmu = perf_pmus__find_by_type(evsel->attr.type);
+
+		TEST_ASSERT_VAL("missing pmu", pmu);
+		TEST_ASSERT_VAL("unexpected pmu", !strncmp(pmu->name, "cpu_", 4));
+		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 0x1a));
+	}
+	return TEST_OK;
+}
+
+static int test__hybrid_raw2(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, 0x1a));
+	return TEST_OK;
+}
+
+static int test__hybrid_cache_event(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff));
+	return TEST_OK;
+}
+
+static int test__checkevent_pmu(struct evlist *evlist)
+{
+
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->core.attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->core.attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->core.attr.config2);
+	TEST_ASSERT_VAL("wrong config3",    0 == evsel->core.attr.config3);
+	/*
+	 * The period value gets configured within evlist__config,
+	 * while this test executes only parse events method.
+	 */
+	TEST_ASSERT_VAL("wrong period",     0 == evsel->core.attr.sample_period);
+
+	return TEST_OK;
+}
+
+struct evlist_test {
+	const char *name;
+	bool (*valid)(void);
+	int (*check)(struct evlist *evlist);
+};
+
+static const struct evlist_test test__hybrid_events[] = {
+	{
+		.name  = "cpu_core/cpu-cycles/",
+		.check = test__hybrid_hw_event_with_pmu,
+		/* 0 */
+	},
+	{
+		.name  = "{cpu_core/cpu-cycles/,cpu_core/instructions/}",
+		.check = test__hybrid_hw_group_event,
+		/* 1 */
+	},
+	{
+		.name  = "{cpu-clock,cpu_core/cpu-cycles/}",
+		.check = test__hybrid_sw_hw_group_event,
+		/* 2 */
+	},
+	{
+		.name  = "{cpu_core/cpu-cycles/,cpu-clock}",
+		.check = test__hybrid_hw_sw_group_event,
+		/* 3 */
+	},
+	{
+		.name  = "{cpu_core/cpu-cycles/k,cpu_core/instructions/u}",
+		.check = test__hybrid_group_modifier1,
+		/* 4 */
+	},
+	{
+		.name  = "r1a",
+		.check = test__hybrid_raw1,
+		/* 5 */
+	},
+	{
+		.name  = "cpu_core/r1a/",
+		.check = test__hybrid_raw2,
+		/* 6 */
+	},
+	{
+		.name  = "cpu_core/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+		/* 7 */
+	},
+	{
+		.name  = "cpu_core/LLC-loads/",
+		.check = test__hybrid_cache_event,
+		/* 8 */
+	},
+};
+
+static int test_event(const struct evlist_test *e)
+{
+	struct parse_events_error err;
+	struct evlist *evlist;
+	int ret;
+
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP\n");
+		return TEST_OK;
+	}
+
+	evlist = evlist__new();
+	if (evlist == NULL) {
+		pr_err("Failed allocation");
+		return TEST_FAIL;
+	}
+	parse_events_error__init(&err);
+	ret = parse_events(evlist, e->name, &err);
+	if (ret) {
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_error__print(&err, e->name);
+		ret = TEST_FAIL;
+		if (strstr(err.str, "can't access trace events"))
+			ret = TEST_SKIP;
+	} else {
+		ret = e->check(evlist);
+	}
+	parse_events_error__exit(&err);
+	evlist__delete(evlist);
+
+	return ret;
+}
+
+static int combine_test_results(int existing, int latest)
+{
+	if (existing == TEST_FAIL)
+		return TEST_FAIL;
+	if (existing == TEST_SKIP)
+		return latest == TEST_OK ? TEST_SKIP : latest;
+	return latest;
+}
+
+static int test_events(const struct evlist_test *events, int cnt)
+{
+	int ret = TEST_OK;
+
+	for (int i = 0; i < cnt; i++) {
+		const struct evlist_test *e = &events[i];
+		int test_ret;
+
+		pr_debug("running test %d '%s'\n", i, e->name);
+		test_ret = test_event(e);
+		if (test_ret != TEST_OK) {
+			pr_debug("Event test failure: test %d '%s'", i, e->name);
+			ret = combine_test_results(ret, test_ret);
+		}
+	}
+
+	return ret;
+}
+
+int test__hybrid(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	if (perf_pmus__num_core_pmus() == 1)
+		return TEST_SKIP;
+
+	return test_events(test__hybrid_events, ARRAY_SIZE(test__hybrid_events));
+}
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 735257d205b5..7b5eb8baf0f2 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -18,14 +18,14 @@ struct test_data {
 	const char *asm_rep;
 };
 
-struct test_data test_data_32[] = {
+const struct test_data test_data_32[] = {
 #include "insn-x86-dat-32.c"
 	{{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee             \trdpkru"},
 	{{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef             \twrpkru"},
 	{{0}, 0, 0, NULL, NULL, NULL},
 };
 
-struct test_data test_data_64[] = {
+const struct test_data test_data_64[] = {
 #include "insn-x86-dat-64.c"
 	{{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee             \trdpkru"},
 	{{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef             \twrpkru"},
@@ -97,7 +97,7 @@ static int get_branch(const char *branch_str)
 	return -1;
 }
 
-static int test_data_item(struct test_data *dat, int x86_64)
+static int test_data_item(const struct test_data *dat, int x86_64)
 {
 	struct intel_pt_insn intel_pt_insn;
 	int op, branch, ret;
@@ -147,9 +147,9 @@ static int test_data_item(struct test_data *dat, int x86_64)
 	return 0;
 }
 
-static int test_data_set(struct test_data *dat_set, int x86_64)
+static int test_data_set(const struct test_data *dat_set, int x86_64)
 {
-	struct test_data *dat;
+	const struct test_data *dat;
 	int ret = 0;
 
 	for (dat = dat_set; dat->expected_length; dat++) {
diff --git a/tools/perf/arch/x86/tests/intel-pt-test.c b/tools/perf/arch/x86/tests/intel-pt-test.c
index 70b7f79396b1..09d61fa736e3 100644
--- a/tools/perf/arch/x86/tests/intel-pt-test.c
+++ b/tools/perf/arch/x86/tests/intel-pt-test.c
@@ -22,7 +22,7 @@
  * @new_ctx: expected new packet context
  * @ctx_unchanged: the packet context must not change
  */
-static struct test_data {
+static const struct test_data {
 	int len;
 	u8 bytes[INTEL_PT_PKT_MAX_SZ];
 	enum intel_pt_pkt_ctx ctx;
@@ -186,7 +186,7 @@ static struct test_data {
 	{0, {0}, 0, {0, 0, 0}, 0, 0 },
 };
 
-static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len)
+static int dump_packet(const struct intel_pt_pkt *packet, const u8 *bytes, int len)
 {
 	char desc[INTEL_PT_PKT_DESC_MAX];
 	int ret, i;
@@ -206,14 +206,14 @@ static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len)
 	return TEST_OK;
 }
 
-static void decoding_failed(struct test_data *d)
+static void decoding_failed(const struct test_data *d)
 {
 	pr_debug("Decoding failed!\n");
 	pr_debug("Decoding:  ");
 	dump_packet(&d->packet, d->bytes, d->len);
 }
 
-static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len,
+static int fail(const struct test_data *d, struct intel_pt_pkt *packet, int len,
 		enum intel_pt_pkt_ctx new_ctx)
 {
 	decoding_failed(d);
@@ -242,7 +242,7 @@ static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len,
 	return TEST_FAIL;
 }
 
-static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet,
+static int test_ctx_unchanged(const struct test_data *d, struct intel_pt_pkt *packet,
 			      enum intel_pt_pkt_ctx ctx)
 {
 	enum intel_pt_pkt_ctx old_ctx = ctx;
@@ -258,7 +258,7 @@ static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet,
 	return TEST_OK;
 }
 
-static int test_one(struct test_data *d)
+static int test_one(const struct test_data *d)
 {
 	struct intel_pt_pkt packet;
 	enum intel_pt_pkt_ctx ctx = d->ctx;
@@ -307,7 +307,7 @@ static int test_one(struct test_data *d)
  */
 int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	struct test_data *d = data;
+	const struct test_data *d = data;
 	int ret;
 
 	for (d = data; d->len; d++) {
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 195ccfdef7aa..005907cb97d8 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -10,6 +10,7 @@ perf-y += evlist.o
 perf-y += mem-events.o
 perf-y += evsel.o
 perf-y += iostat.o
+perf-y += env.o
 
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 330d03216b0e..354780ff1605 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -10,6 +10,7 @@
 #include "../../../util/header.h"
 #include "../../../util/debug.h"
 #include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
 #include "../../../util/auxtrace.h"
 #include "../../../util/intel-pt.h"
 #include "../../../util/intel-bts.h"
@@ -25,8 +26,8 @@ struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
 	bool found_pt = false;
 	bool found_bts = false;
 
-	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
-	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+	intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
+	intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type)
diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c
new file mode 100644
index 000000000000..3e537ffb1353
--- /dev/null
+++ b/tools/perf/arch/x86/util/env.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "linux/string.h"
+#include "util/env.h"
+#include "env.h"
+
+bool x86__is_amd_cpu(void)
+{
+	struct perf_env env = { .total_mem = 0, };
+	static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */
+
+	if (is_amd)
+		goto ret;
+
+	perf_env__cpuid(&env);
+	is_amd = env.cpuid && strstarts(env.cpuid, "AuthenticAMD") ? 1 : -1;
+	perf_env__exit(&env);
+ret:
+	return is_amd >= 1 ? true : false;
+}
diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h
new file mode 100644
index 000000000000..d78f080b6b3f
--- /dev/null
+++ b/tools/perf/arch/x86/util/env.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_ENV_H
+#define _X86_ENV_H
+
+bool x86__is_amd_cpu(void);
+
+#endif /* _X86_ENV_H */
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index d4193479a364..cbd582182932 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -1,38 +1,42 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include "util/pmu.h"
+#include "util/pmus.h"
 #include "util/evlist.h"
 #include "util/parse-events.h"
 #include "util/event.h"
-#include "util/pmu-hybrid.h"
 #include "topdown.h"
+#include "evsel.h"
 
 static int ___evlist__add_default_attrs(struct evlist *evlist,
 					struct perf_event_attr *attrs,
 					size_t nr_attrs)
 {
-	struct perf_cpu_map *cpus;
-	struct evsel *evsel, *n;
-	struct perf_pmu *pmu;
 	LIST_HEAD(head);
 	size_t i = 0;
 
 	for (i = 0; i < nr_attrs; i++)
 		event_attr_init(attrs + i);
 
-	if (!perf_pmu__has_hybrid())
+	if (perf_pmus__num_core_pmus() == 1)
 		return evlist__add_attrs(evlist, attrs, nr_attrs);
 
 	for (i = 0; i < nr_attrs; i++) {
+		struct perf_pmu *pmu = NULL;
+
 		if (attrs[i].type == PERF_TYPE_SOFTWARE) {
-			evsel = evsel__new(attrs + i);
+			struct evsel *evsel = evsel__new(attrs + i);
+
 			if (evsel == NULL)
 				goto out_delete_partial_list;
 			list_add_tail(&evsel->core.node, &head);
 			continue;
 		}
 
-		perf_pmu__for_each_hybrid_pmu(pmu) {
+		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+			struct perf_cpu_map *cpus;
+			struct evsel *evsel;
+
 			evsel = evsel__new(attrs + i);
 			if (evsel == NULL)
 				goto out_delete_partial_list;
@@ -50,8 +54,12 @@ static int ___evlist__add_default_attrs(struct evlist *evlist,
 	return 0;
 
 out_delete_partial_list:
-	__evlist__for_each_entry_safe(&head, n, evsel)
-		evsel__delete(evsel);
+	{
+		struct evsel *evsel, *n;
+
+		__evlist__for_each_entry_safe(&head, n, evsel)
+			evsel__delete(evsel);
+	}
 	return -1;
 }
 
@@ -67,8 +75,7 @@ int arch_evlist__add_default_attrs(struct evlist *evlist,
 
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 {
-	if (topdown_sys_has_perf_metrics() &&
-	    (!lhs->pmu_name || !strncmp(lhs->pmu_name, "cpu", 3))) {
+	if (topdown_sys_has_perf_metrics() && evsel__sys_has_perf_metrics(lhs)) {
 		/* Ensure the topdown slots comes first. */
 		if (strcasestr(lhs->name, "slots"))
 			return -1;
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ea3972d785d1..512c2d885d24 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -4,9 +4,11 @@
 #include "util/evsel.h"
 #include "util/env.h"
 #include "util/pmu.h"
+#include "util/pmus.h"
 #include "linux/string.h"
 #include "evsel.h"
 #include "util/debug.h"
+#include "env.h"
 
 #define IBS_FETCH_L3MISSONLY   (1ULL << 59)
 #define IBS_OP_L3MISSONLY      (1ULL << 16)
@@ -16,26 +18,6 @@ void arch_evsel__set_sample_weight(struct evsel *evsel)
 	evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
 }
 
-void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
-{
-	struct perf_env env = { .total_mem = 0, } ;
-
-	if (!perf_env__cpuid(&env))
-		return;
-
-	/*
-	 * On AMD, precise cycles event sampling internally uses IBS pmu.
-	 * But IBS does not have filtering capabilities and perf by default
-	 * sets exclude_guest = 1. This makes IBS pmu event init fail and
-	 * thus perf ends up doing non-precise sampling. Avoid it by clearing
-	 * exclude_guest.
-	 */
-	if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
-		attr->exclude_guest = 0;
-
-	free(env.cpuid);
-}
-
 /* Check whether the evsel's PMU supports the perf metrics */
 bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 {
@@ -50,7 +32,7 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 	 * should be good enough to detect the perf metrics feature.
 	 */
 	if ((evsel->core.attr.type == PERF_TYPE_RAW) &&
-	    pmu_have_event(pmu_name, "slots"))
+	    perf_pmus__have_event(pmu_name, "slots"))
 		return true;
 
 	return false;
@@ -97,29 +79,16 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
 {
 	struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
 	static int warned_once;
-	/* 0: Uninitialized, 1: Yes, -1: No */
-	static int is_amd;
 
-	if (warned_once || is_amd == -1)
+	if (warned_once || !x86__is_amd_cpu())
 		return;
 
-	if (!is_amd) {
-		struct perf_env *env = evsel__env(evsel);
-
-		if (!perf_env__cpuid(env) || !env->cpuid ||
-		    !strstarts(env->cpuid, "AuthenticAMD")) {
-			is_amd = -1;
-			return;
-		}
-		is_amd = 1;
-	}
-
 	evsel_pmu = evsel__find_pmu(evsel);
 	if (!evsel_pmu)
 		return;
 
-	ibs_fetch_pmu = perf_pmu__find("ibs_fetch");
-	ibs_op_pmu = perf_pmu__find("ibs_op");
+	ibs_fetch_pmu = perf_pmus__find("ibs_fetch");
+	ibs_op_pmu = perf_pmus__find("ibs_op");
 
 	if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
 		if (attr->config & IBS_FETCH_L3MISSONLY) {
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 439c2956f3e7..d2c8cac11470 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -17,7 +17,7 @@
 #include "../../../util/evlist.h"
 #include "../../../util/mmap.h"
 #include "../../../util/session.h"
-#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
 #include "../../../util/debug.h"
 #include "../../../util/record.h"
 #include "../../../util/tsc.h"
@@ -416,7 +416,7 @@ out_err:
 
 struct auxtrace_record *intel_bts_recording_init(int *err)
 {
-	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+	struct perf_pmu *intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
 	struct intel_bts_recording *btsr;
 
 	if (!intel_bts_pmu)
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 17336da08b58..74b70fd379df 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -23,7 +23,7 @@
 #include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
 #include "../../../util/parse-events.h"
-#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
 #include "../../../util/debug.h"
 #include "../../../util/auxtrace.h"
 #include "../../../util/perf_api_probe.h"
@@ -1185,7 +1185,7 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
-	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+	struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
 	struct intel_pt_recording *ptr;
 
 	if (!intel_pt_pmu)
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index f683ac702247..a8a782bcb121 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "util/pmu.h"
+#include "util/pmus.h"
 #include "util/env.h"
 #include "map_symbol.h"
 #include "mem-events.h"
 #include "linux/string.h"
+#include "env.h"
 
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
@@ -26,28 +28,12 @@ static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
 	E("mem-ldst",	"ibs_op//",	"ibs_op"),
 };
 
-static int perf_mem_is_amd_cpu(void)
-{
-	struct perf_env env = { .total_mem = 0, };
-
-	perf_env__cpuid(&env);
-	if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
-		return 1;
-	return -1;
-}
-
 struct perf_mem_event *perf_mem_events__ptr(int i)
 {
-	/* 0: Uninitialized, 1: Yes, -1: No */
-	static int is_amd;
-
 	if (i >= PERF_MEM_EVENTS__MAX)
 		return NULL;
 
-	if (!is_amd)
-		is_amd = perf_mem_is_amd_cpu();
-
-	if (is_amd == 1)
+	if (x86__is_amd_cpu())
 		return &perf_mem_events_amd[i];
 
 	return &perf_mem_events_intel[i];
@@ -55,13 +41,13 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
 
 bool is_mem_loads_aux_event(struct evsel *leader)
 {
-	if (perf_pmu__find("cpu")) {
-		if (!pmu_have_event("cpu", "mem-loads-aux"))
-			return false;
-	} else if (perf_pmu__find("cpu_core")) {
-		if (!pmu_have_event("cpu_core", "mem-loads-aux"))
-			return false;
-	}
+	struct perf_pmu *pmu = perf_pmus__find("cpu");
+
+	if (!pmu)
+		pmu = perf_pmus__find("cpu_core");
+
+	if (pmu && !perf_pmu__have_event(pmu, "mem-loads-aux"))
+		return false;
 
 	return leader->core.attr.config == MEM_LOADS_AUX;
 }
@@ -82,7 +68,7 @@ char *perf_mem_events__name(int i, char *pmu_name)
 			pmu_name = (char *)"cpu";
 		}
 
-		if (pmu_have_event(pmu_name, "mem-loads-aux")) {
+		if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) {
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
 				  MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
 				  perf_mem_events__loads_ldlat);
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 0ed177991ad0..8ad4112ad10c 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -10,7 +10,7 @@
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
 #include "../../../util/pmu.h"
-#include "../../../util/pmu-hybrid.h"
+#include "../../../util/pmus.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
@@ -286,20 +286,25 @@ uint64_t arch__intr_reg_mask(void)
 		.disabled 		= 1,
 		.exclude_kernel		= 1,
 	};
-	struct perf_pmu *pmu;
 	int fd;
 	/*
 	 * In an unnamed union, init it here to build on older gcc versions
 	 */
 	attr.sample_period = 1;
 
-	if (perf_pmu__has_hybrid()) {
+	if (perf_pmus__num_core_pmus() > 1) {
+		struct perf_pmu *pmu = NULL;
+		__u64 type = PERF_TYPE_RAW;
+
 		/*
 		 * The same register set is supported among different hybrid PMUs.
 		 * Only check the first available one.
 		 */
-		pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list);
-		attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+			type = pmu->type;
+			break;
+		}
+		attr.config |= type << PERF_PMU_TYPE_SHIFT;
 	}
 
 	event_attr_init(&attr);
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 3c0de3370d7e..65d8cdff4d5f 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -14,6 +14,8 @@
 #include "../../../util/intel-bts.h"
 #include "../../../util/pmu.h"
 #include "../../../util/fncache.h"
+#include "../../../util/pmus.h"
+#include "env.h"
 
 struct pmu_alias {
 	char *name;
@@ -168,3 +170,13 @@ char *pmu_find_alias_name(const char *name)
 
 	return __pmu_find_alias_name(name);
 }
+
+int perf_pmus__num_mem_pmus(void)
+{
+	/* AMD uses IBS OP pmu and not a core PMU for perf mem/c2c */
+	if (x86__is_amd_cpu())
+		return 1;
+
+	/* Intel uses core pmus for perf mem/c2c */
+	return perf_pmus__num_core_pmus();
+}
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index 9ad5e5c7bd27..3f9a267d4501 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -2,6 +2,7 @@
 #include "api/fs/fs.h"
 #include "util/evsel.h"
 #include "util/pmu.h"
+#include "util/pmus.h"
 #include "util/topdown.h"
 #include "topdown.h"
 #include "evsel.h"
@@ -22,8 +23,8 @@ bool topdown_sys_has_perf_metrics(void)
 	 * The slots event is only available when the core PMU
 	 * supports the perf metrics feature.
 	 */
-	pmu = perf_pmu__find_by_type(PERF_TYPE_RAW);
-	if (pmu && pmu_have_event(pmu->name, "slots"))
+	pmu = perf_pmus__find_by_type(PERF_TYPE_RAW);
+	if (pmu && perf_pmu__have_event(pmu, "slots"))
 		has_perf_metrics = true;
 
 	cached = true;