perf test attr: Report the failures again and cope with more than one core PMU

index ae92061d611ded68..fbe0faa8cdb6a8f4 100644
@@ -4,7 +4,7 @@ args    = --no-bpf-event --call-graph dwarf -- kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]
-sample_type=45359
+sample_type=12583
 exclude_callchain_user=1
 sample_stack_user=8192
 # TODO different for each arch, no support for that now

index 86a940d7895d7404..b43d9fe3af75c096 100644
@@ -3,6 +3,7 @@ command = record
 args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_until = 6.12
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index 4748ab7bf68437c7..3def72161820dca3 100644
@@ -3,6 +3,7 @@ command = record
 args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index e0432244a0eb7f6c..227c18bb221c4b2f 100644
@@ -3,6 +3,7 @@ command = record
 args    = --no-bpf-event -c 10000 -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index eeb1db392bc9ceac..a57c7ee8aaa4f9c9 100644
@@ -2,6 +2,7 @@
 command = record
 args    = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index 891d41a7bddf785a..fb6e664eeacc10ef 100644
@@ -3,6 +3,7 @@ command = record
 args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_until = 6.12
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index 249be884959eaaba..7b90b4411d8f4b90 100644
@@ -3,6 +3,7 @@ command = record
 args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
+requires = core-pmu
 
 [event-1:base-record]
 fd=1

index a2c76d10b2bb2a15..9d242e93e3a92009 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -e cycles -C 0 kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 [event:base-stat]
 # events are disabled by default when attached to cpu

index 69867d049fda926f..277897bd2626a41f 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -e cycles kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 [event:base-stat]
 optional=1

index 8dd27c1fb661fb77..74691188e859a169 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
 [event1:base-stat]

index 12a2ebf4e64a0077..d9a6236054f2dfb1 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -d kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 
 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK

index 66ea25b7d38f8d59..582a30289ccfa6df 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -dd kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 
 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK

index 4a27bbfb9f87a538..2d0fca8b5020f504 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -ddd kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 
 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK

index 1746751123dcb2c4..3d8b44ba42d6ae19 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 [event-1:base-stat]
 fd=1

index 924fbb9300d16259..38f746855b1b3e11 100644
@@ -2,6 +2,7 @@
 command = stat
 args    = -i -e cycles kill >/dev/null 2>&1
 ret     = 1
+requires = core-pmu
 
 [event:base-stat]
 inherit=0

80 lines not on this page · raw message

index 67c4ca76b85d5611..c7b49cdf87297177 100644
@@ -49,10 +49,10 @@ Following tests are defined (with perf commands):
   perf record --call-graph dwarf kill		(test-record-graph-dwarf)
   perf record --call-graph fp kill              (test-record-graph-fp)
   perf record --call-graph fp kill              (test-record-graph-fp-aarch64)
-  perf record -e '{cycles,instructions}' kill   (test-record-group1)
-  perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
-  perf record -e '{cycles,cache-misses}:S' kill (test-record-group-sampling1)
-  perf record -c 10000 -e '{cycles,cache-misses}:S' kill (test-record-group-sampling2)
+  perf record -e '{cycles,default_core/legacy-hardware-config=1/}' kill (test-record-group1)
+  perf record -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill (test-record-group2)
+  perf record -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill (test-record-group-sampling1)
+  perf record -c 10000 -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill (test-record-group-sampling2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)

@@ -67,5 +67,5 @@ Following tests are defined (with perf commands):
   perf stat -d kill                             (test-stat-detailed-1)
   perf stat -dd kill                            (test-stat-detailed-2)
   perf stat -ddd kill                           (test-stat-detailed-3)
-  perf stat -e '{cycles,instructions}' kill     (test-stat-group1)
+  perf stat -e '{cycles,default_core/legacy-hardware-config=1/}' kill (test-stat-group1)
   perf stat -i -e cycles kill                   (test-stat-no-inherit)

index b43d9fe3af75c096..ed47dd1e5984535b 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_until = 6.12
 requires = core-pmu

@@ -16,7 +16,7 @@ inherit=0
 fd=2
 group_fd=1
 
-# cache-misses
+# cache-misses, explicitly requested with the legacy hardware encoding
 type=0
 config=3
 

index 3def72161820dca3..9cf013dc03dd0309 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
 requires = core-pmu

@@ -31,7 +31,7 @@ inherit=1
 fd=2
 group_fd=1
 
-# cache-misses
+# cache-misses, explicitly requested with the legacy hardware encoding
 type=0
 config=3
 

index 227c18bb221c4b2f..bd1eb4161e4aee46 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -c 10000 -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -c 10000 -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
 requires = core-pmu

@@ -37,7 +37,7 @@ write_backward=0
 fd=2
 group_fd=1
 
-# cache-misses
+# cache-misses, explicitly requested with the legacy hardware encoding
 type=0
 config=3
 

index a57c7ee8aaa4f9c9..5fdd5288555f32ea 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=1/}' kill >/dev/null 2>&1
 ret     = 1
 requires = core-pmu
 

index fb6e664eeacc10ef..e7274108f5fd7e7b 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_until = 6.12
 requires = core-pmu

index 7b90b4411d8f4b90..e74fd3a48ac9094f 100644
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill >/dev/null 2>&1
 ret     = 1
 kernel_since = 6.12
 requires = core-pmu

index 3d8b44ba42d6ae19..7a31b27933f11959 100644
@@ -1,6 +1,6 @@
 [config]
 command = stat
-args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+args    = -e '{cycles,default_core/legacy-hardware-config=1/}' kill >/dev/null 2>&1
 ret     = 1
 requires = core-pmu
 

new file mode 100644
index 0000000000000000..9bcb8ab3687ff9fb
@@ -0,0 +1,45 @@
+[event]
+fd=1
+group_fd=-1
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
+cpu=*
+type=0
+size=176
+config=0
+sample_period=0
+sample_type=65536
+# The default and -d/-dd/-ddd metrics open part of their events in groups:
+# the members get read_format=15 and are enabled right away, the standalone
+# ones keep read_format=3 and wait for the exec, and the leaders get 15 when
+# their group has members, 3 when alone, as create_perf_stat_counter() goes.
+read_format=3|15
+disabled=0|1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0|1
+exclude_hv=0|1
+exclude_idle=0
+mmap=0
+comm=0
+freq=0
+inherit_stat=0
+enable_on_exec=0|1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=0
+exclude_host=0|1
+exclude_guest=0|1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0

259 lines not on this page · raw message

292 lines not on this page · raw message

340 lines not on this page · raw message

356 lines not on this page · raw message

index b55c9b881e59852f..f254d03c1b253c7a 100644
@@ -353,7 +353,7 @@ class Test(object):
             else:
                 raise Unsup(self)
 
-    def compare(self, expect, result):
+    def compare(self, expect, result, strict_groups=True):
         match = {}
 
         log.debug("  compare")

@@ -387,8 +387,9 @@ class Test(object):
 
             match[exp_name] = exp_list
 
-        # For each defined group in the expected events
-        # check we match the same group in the result.
+        # Check that each expected group is matched in the result; an event
+        # opened in a group may match an expectation that doesn't declare
+        # one, as those only verify the event attributes.
         for exp_name, exp_event in expect.items():
             group = exp_event.group
 

@@ -397,6 +398,8 @@ class Test(object):
 
             for res_name in match[exp_name]:
                 res_group = result[res_name].group
+                if res_group == '' and not strict_groups:
+                    continue
                 if res_group not in match[group]:
                     raise Fail(self, 'group failure')
 

@@ -435,7 +438,7 @@ class Test(object):
 
             # do the expectation - results matching - both ways
             self.compare(self.expect, self.result)
-            self.compare(self.result, self.expect)
+            self.compare(self.result, self.expect, strict_groups=False)
 
         finally:
             # cleanup

index f254d03c1b253c7a..70ff73585cb3ffa9 100644
@@ -57,6 +57,32 @@ def core_pmu_available():
 
     return True
 
+PERF_TYPE_HARDWARE = 0
+PERF_TYPE_HW_CACHE = 3
+
+# The legacy event types, where perf may qualify 'config' with the core PMU
+# type in its top 32 bits when there is more than one core PMU.
+LEGACY_TYPES = (str(PERF_TYPE_HARDWARE), str(PERF_TYPE_HW_CACHE))
+
+def hide_core_pmu_type(value):
+    """
+    The kernel can be told which core PMU a legacy type event is meant for by
+    putting its type in the top 32 bits of 'config', which perf only does when
+    there is more than one core PMU, so take those bits out to keep the
+    expectations written for the single core PMU case matching on
+    heterogeneous machines.
+    """
+    hidden = []
+
+    for alternative in value.split('|'):
+        try:
+            alternative = str(int(alternative, 0) & 0xffffffff)
+        except ValueError:
+            pass
+        hidden.append(alternative)
+
+    return '|'.join(hidden)
+
 class Fail(Exception):
     def __init__(self, test, msg):
         self.msg = msg

@@ -130,12 +156,33 @@ class Event(dict):
         self.add(base)
         self.add(data)
 
+    def hide_core_pmu_type_terms(self, other):
+        """
+        Is this a legacy type event? Then the core PMU type that perf may have
+        put in the top 32 bits of 'config' to tell the kernel which core PMU it
+        wants isn't part of what we asked for, see hide_core_pmu_type().
+        """
+        for event in (self, other):
+            for type in event.get('type', '').split('|'):
+                if type in LEGACY_TYPES:
+                    return True
+
+        return False
+
+    def hide_core_pmu_type(self, term, value, other):
+        if term == 'config' and self.hide_core_pmu_type_terms(other):
+            return hide_core_pmu_type(value)
+
+        return value
+
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s", t, self[t], other[t])
             if t not in self or t not in other:
                 return False
-            if not data_equal(self[t], other[t]):
+            exp = self.hide_core_pmu_type(t, self[t], other)
+            got = self.hide_core_pmu_type(t, other[t], other)
+            if not data_equal(exp, got):
                 return False
         return True
 

@@ -148,7 +195,9 @@ class Event(dict):
         for t in Event.terms:
             if t not in self or t not in other:
                 continue
-            if not data_equal(self[t], other[t]):
+            exp = self.hide_core_pmu_type(t, self[t], other)
+            got = self.hide_core_pmu_type(t, other[t], other)
+            if not data_equal(exp, got):
                 log.warning("expected %s=%s, got %s", t, self[t], other[t])
 
 def parse_version(version):

index 70ff73585cb3ffa9..151b884670952e9f 100644
@@ -64,24 +64,31 @@ PERF_TYPE_HW_CACHE = 3
 # type in its top 32 bits when there is more than one core PMU.
 LEGACY_TYPES = (str(PERF_TYPE_HARDWARE), str(PERF_TYPE_HW_CACHE))
 
-def hide_core_pmu_type(value):
+def mask_bits(value, bits):
     """
-    The kernel can be told which core PMU a legacy type event is meant for by
-    putting its type in the top 32 bits of 'config', which perf only does when
-    there is more than one core PMU, so take those bits out to keep the
-    expectations written for the single core PMU case matching on
-    heterogeneous machines.
+    Take the bits in 'bits' out of each of the '|'-separated alternatives in
+    'value', keeping the rest of the expression, wildcards included.
     """
-    hidden = []
+    masked = []
 
     for alternative in value.split('|'):
         try:
-            alternative = str(int(alternative, 0) & 0xffffffff)
+            alternative = str(int(alternative, 0) & ~bits)
         except ValueError:
             pass
-        hidden.append(alternative)
+        masked.append(alternative)
 
-    return '|'.join(hidden)
+    return '|'.join(masked)
+
+def hide_core_pmu_type(value):
+    """
+    The kernel can be told which core PMU a legacy type event is meant for by
+    putting its type in the top 32 bits of 'config', which perf only does when
+    there is more than one core PMU, so take those bits out to keep the
+    expectations written for the single core PMU case matching on
+    heterogeneous machines.
+    """
+    return mask_bits(value, 0xffffffff00000000)
 
 class Fail(Exception):
     def __init__(self, test, msg):

index 151b884670952e9f..e911684428b1b74b 100644
@@ -59,6 +59,8 @@ def core_pmu_available():
 
 PERF_TYPE_HARDWARE = 0
 PERF_TYPE_HW_CACHE = 3
+PERF_SAMPLE_ID = 1 << 6
+PERF_SAMPLE_IDENTIFIER = 1 << 16
 
 # The legacy event types, where perf may qualify 'config' with the core PMU
 # type in its top 32 bits when there is more than one core PMU.

@@ -90,6 +92,49 @@ def hide_core_pmu_type(value):
     """
     return mask_bits(value, 0xffffffff00000000)
 
+# The two sample id bits mean the same thing here: how the samples of the
+# events in the evlist get associated with the event that produced them.
+SAMPLE_ID_BITS = PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER
+
+# No real sample_type bit is this high, so it can stand for "either of the
+# sample id bits" when comparing the two sides.
+SAMPLE_ID_EITHER = 1 << 40
+
+def hide_sample_id(expected, recorded):
+    """
+    perf asks for a way to tell the samples apart, PERF_SAMPLE_IDENTIFIER where
+    available, PERF_SAMPLE_ID otherwise, see evlist__config(): whenever the
+    evlist has more than one event, and when asked to outright, with
+    --sample-identifier, by an auxtrace session, or by record__config() for a
+    pipe run, none of which depends on the sample types, as those only choose
+    between the two bits:
+    with more than one core PMU the dummy tracking events make the sample types
+    differ, so IDENTIFIER is asked for even for events whose expectations ask
+    for ID, written on a machine with a single core PMU.
+
+    So treat the two as the same thing: when the expectation asks for either
+    of them, ask for "an id of some sort" on both sides, and when the
+    expectation doesn't ask for any, take the bits out of what got recorded.
+    """
+    try:
+        asked = int(expected, 0) & SAMPLE_ID_BITS
+    except ValueError:
+        # The expectation is a wildcard or a set of alternatives.
+        return expected, recorded
+
+    try:
+        recorded_id_bits = int(recorded, 0) & SAMPLE_ID_BITS
+    except ValueError:
+        # The recorded side is a wildcard or a set of alternatives.
+        return expected, mask_bits(recorded, SAMPLE_ID_BITS)
+
+    if not asked:
+        return expected, mask_bits(recorded, SAMPLE_ID_BITS)
+
+    return (str(int(expected, 0) & ~SAMPLE_ID_BITS | SAMPLE_ID_EITHER),
+            str(int(recorded, 0) & ~SAMPLE_ID_BITS |
+                (SAMPLE_ID_EITHER if recorded_id_bits else 0)))
+
 class Fail(Exception):
     def __init__(self, test, msg):
         self.msg = msg

@@ -182,13 +227,33 @@ class Event(dict):
 
         return value
 
+    def hide_event_count_dependent_terms(self, term, expected, recorded):
+        if term == 'sample_type':
+            return hide_sample_id(expected, recorded)
+
+        return expected, recorded
+
+    def recorded_side(self, other):
+        """
+        Which one is what perf recorded? Both directions get compared, see
+        Test.compare(), so this can't be taken from the arguments' order.
+        """
+        if getattr(other, 'recorded', False):
+            return other
+
+        return self if getattr(self, 'recorded', False) else None
+
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s", t, self[t], other[t])
             if t not in self or t not in other:
                 return False
-            exp = self.hide_core_pmu_type(t, self[t], other)
-            got = self.hide_core_pmu_type(t, other[t], other)
+            recorded = self.recorded_side(other)
+            expected = other if recorded is self else self
+            exp = self.hide_core_pmu_type(t, expected[t], recorded or expected)
+            got = self.hide_core_pmu_type(t, (recorded or self)[t], expected)
+            if recorded is not None:
+                exp, got = self.hide_event_count_dependent_terms(t, exp, got)
             if not data_equal(exp, got):
                 return False
         return True

@@ -202,10 +267,14 @@ class Event(dict):
         for t in Event.terms:
             if t not in self or t not in other:
                 continue
-            exp = self.hide_core_pmu_type(t, self[t], other)
-            got = self.hide_core_pmu_type(t, other[t], other)
+            recorded = self.recorded_side(other)
+            expected = other if recorded is self else self
+            exp = self.hide_core_pmu_type(t, expected[t], recorded or expected)
+            got = self.hide_core_pmu_type(t, (recorded or self)[t], expected)
+            if recorded is not None:
+                exp, got = self.hide_event_count_dependent_terms(t, exp, got)
             if not data_equal(exp, got):
-                log.warning("expected %s=%s, got %s", t, self[t], other[t])
+                log.warning("expected %s=%s, got %s", t, exp, got)
 
 def parse_version(version):
     if not version:

@@ -487,6 +556,8 @@ class Test(object):
             log.debug("  loading result events")
             for f in glob.glob(tempdir + '/event*'):
                 self.load_events(f, self.result)
+            for event in self.result.values():
+                event.recorded = True
 
             # resolve group_fd to event names
             self.resolve_groups(self.expect)

index e911684428b1b74b..222ce6f598831e3f 100644
@@ -61,6 +61,21 @@ PERF_TYPE_HARDWARE = 0
 PERF_TYPE_HW_CACHE = 3
 PERF_SAMPLE_ID = 1 << 6
 PERF_SAMPLE_IDENTIFIER = 1 << 16
+PERF_TYPE_SOFTWARE = 1
+PERF_COUNT_SW_DUMMY = 9
+
+def is_dummy_tracking_event(event):
+    """
+    Is this the dummy event perf opens to carry the tracking events (mmap,
+    comm, task) when the requested ones can't, like when there is more than one
+    core PMU and each core PMU's events run on only part of the CPUs?
+    """
+    return (event.get('type') == str(PERF_TYPE_SOFTWARE) and
+            event.get('config') == str(PERF_COUNT_SW_DUMMY))
+
+# With more than one core PMU the tracking terms go to the dummy tracking event,
+# leaving the requested events without them, so they can't be matched there.
+TRACKING_TERMS = ['mmap', 'comm', 'task', 'mmap_data']
 
 # The legacy event types, where perf may qualify 'config' with the core PMU
 # type in its top 32 bits when there is more than one core PMU.

@@ -243,11 +258,26 @@ class Event(dict):
 
         return self if getattr(self, 'recorded', False) else None
 
+    def hide_tracking_via_dummy(self, term, other):
+        """
+        The tracking terms are set on the tracking event, which is the dummy
+        event when there is more than one core PMU, leaving the requested
+        events without them, nothing to match on then.
+        """
+        if term not in TRACKING_TERMS:
+            return False
+
+        return (getattr(self, 'tracking_moved_to_dummy', False) or
+                getattr(other, 'tracking_moved_to_dummy', False))
+
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s", t, self[t], other[t])
             if t not in self or t not in other:
                 return False
+            if self.hide_tracking_via_dummy(t, other):
+                continue
+
             recorded = self.recorded_side(other)
             expected = other if recorded is self else self
             exp = self.hide_core_pmu_type(t, expected[t], recorded or expected)

@@ -267,6 +297,9 @@ class Event(dict):
         for t in Event.terms:
             if t not in self or t not in other:
                 continue
+            if self.hide_tracking_via_dummy(t, other):
+                continue
+
             recorded = self.recorded_side(other)
             expected = other if recorded is self else self
             exp = self.hide_core_pmu_type(t, expected[t], recorded or expected)

@@ -478,6 +511,27 @@ class Test(object):
             else:
                 raise Unsup(self)
 
+    def drop_dummy_tracking_events(self):
+        """
+        Leave out the dummy event perf itself opened, see
+        is_dummy_tracking_event(), unless the expectations ask for one.
+        """
+        if any(is_dummy_tracking_event(e) for e in self.expect.values()):
+            return
+
+        if not any(is_dummy_tracking_event(e) for e in self.result.values()):
+            return
+
+        for name, event in list(self.result.items()):
+            if is_dummy_tracking_event(event):
+                log.debug("      dropping dummy tracking event [%s]", name)
+                del self.result[name]
+
+        # The tracking terms got carried by the dropped dummies, flag the
+        # remaining events so that the match leaves those terms out.
+        for event in self.result.values():
+            event.tracking_moved_to_dummy = True
+
     def compare(self, expect, result, strict_groups=True):
         match = {}
 

@@ -559,6 +613,8 @@ class Test(object):
             for event in self.result.values():
                 event.recorded = True
 
+            self.drop_dummy_tracking_events()
+
             # resolve group_fd to event names
             self.resolve_groups(self.expect)
             self.resolve_groups(self.result)

index 222ce6f598831e3f..65b1e655a2bcb505 100644
@@ -532,6 +532,44 @@ class Test(object):
         for event in self.result.values():
             event.tracking_moved_to_dummy = True
 
+    def drop_other_core_pmu_events(self, devices='/sys/bus/event_source/devices'):
+        """
+        Leave out the events of the other core PMUs, which have their own
+        encodings, when the expectations name one of the core PMUs.
+        """
+        asked = set()
+        for event in self.expect.values():
+            types = event.get('type', '').split('|')
+            if '*' in types:
+                return
+            asked.update(types)
+
+        try:
+            names = os.listdir(devices)
+        except OSError:
+            return
+
+        core = set()
+        for name in names:
+            path = os.path.join(devices, name)
+            has_cpus = os.path.exists(os.path.join(path, 'cpus'))
+            if name not in ('cpu', 'cpum_cf') and not has_cpus:
+                continue
+            try:
+                with open(os.path.join(path, 'type'), encoding='utf-8') as f:
+                    core.add(f.read().strip())
+            except OSError:
+                pass
+
+        if not core & asked:
+            return
+
+        others = core - asked
+        for name, event in list(self.result.items()):
+            if event.get('type') in others:
+                log.debug("      dropping other core PMU event [%s]", name)
+                del self.result[name]
+
     def compare(self, expect, result, strict_groups=True):
         match = {}
 

@@ -614,6 +652,7 @@ class Test(object):
                 event.recorded = True
 
             self.drop_dummy_tracking_events()
+            self.drop_other_core_pmu_events()
 
             # resolve group_fd to event names
             self.resolve_groups(self.expect)

index 65b1e655a2bcb505..3bf07d4df95987d8 100644
@@ -115,6 +115,50 @@ SAMPLE_ID_BITS = PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER
 # sample id bits" when comparing the two sides.
 SAMPLE_ID_EITHER = 1 << 40
 
+PERF_FORMAT_GROUP = 1 << 3
+
+def core_pmu_count():
+    """
+    How many core PMUs does perf see?  An event with no PMU named in it
+    becomes one event per core PMU, see parse_events_multi_pmu_add(), and
+    that is the expansion that leaves the clones for the other core PMUs
+    without any group members and that makes the kernel qualify 'config'
+    with the type of the PMU it is for, so this is the number of events perf
+    makes of 'cycles'.  None when there is no binding to ask, as in
+    core_pmu_available().
+    """
+    try:
+        import perf
+        parse_events = perf.parse_events
+    except (ImportError, AttributeError):
+        return None
+
+    try:
+        return len(parse_events('cycles'))
+    except OSError:
+        # No PMU that can count it, see core_pmu_available().
+        return None
+
+SINGLE_CORE_PMU = core_pmu_count() == 1
+
+def hide_group_format(expected, recorded):
+    """
+    read_format's PERF_FORMAT_GROUP bit asks for the group members to be read
+    along with the leader, which aside from this bit is verified with the
+    fd/group_fd based group checking, and with more than one core PMU a group
+    whose members are pinned to one of them, say 'default_core', leaves the
+    clones for the other core PMUs without any members, so that bit isn't
+    there: whether it is there is a consequence of how the evlist got
+    expanded to more than one core PMU, not of what the expectations are
+    about, so take it out on both sides.  On a machine with a single core PMU
+    there is nothing to expand, so the expectations keep verifying it.
+    """
+    if SINGLE_CORE_PMU:
+        return expected, recorded
+
+    return (mask_bits(expected, PERF_FORMAT_GROUP),
+            mask_bits(recorded, PERF_FORMAT_GROUP))
+
 def hide_sample_id(expected, recorded):
     """
     perf asks for a way to tell the samples apart, PERF_SAMPLE_IDENTIFIER where

@@ -245,6 +289,8 @@ class Event(dict):
     def hide_event_count_dependent_terms(self, term, expected, recorded):
         if term == 'sample_type':
             return hide_sample_id(expected, recorded)
+        if term == 'read_format':
+            return hide_group_format(expected, recorded)
 
         return expected, recorded
 

index 3bf07d4df95987d8..ee78c912d94693dd 100644
@@ -209,10 +209,13 @@ class Notest(Exception):
         return '[%s] \'%s\'' % (self.arch, self.test.path)
 
 class Unsup(Exception):
-    def __init__(self, test):
+    def __init__(self, test, ret, expected):
         self.test = test
+        self.ret = ret
+        self.expected = expected
     def getMsg(self):
-        return '\'%s\'' % self.test.path
+        return '\'%s\' exit %d, expected %s, likely a missing capability' % (
+            self.test.path, self.ret, self.expected)
 
 class Event(dict):
     terms = [

@@ -425,13 +428,17 @@ class Test(object):
 
     def skip_test_kernel_since(self):
         if not self.kernel_since:
-            return False
-        return not self.kernel_since <= parse_version(platform.release())
+            return None
+        if self.kernel_since <= parse_version(platform.release()):
+            return None
+        return "kernel older than %d.%d" % tuple(self.kernel_since)
 
     def skip_test_kernel_until(self):
         if not self.kernel_until:
-            return False
-        return not parse_version(platform.release()) < self.kernel_until
+            return None
+        if parse_version(platform.release()) < self.kernel_until:
+            return None
+        return "kernel newer than %d.%d" % tuple(self.kernel_until)
 
     def skip_test_auxv(self):
         def new_auxv(a, pattern):

@@ -447,18 +454,20 @@ class Test(object):
             return (items[0], value)
 
         if not self.auxv:
-            return False
+            return None
         auxv = subprocess.check_output("LD_SHOW_AUXV=1 sleep 0", shell=True) \
                .decode(sys.stdout.encoding)
         pattern = re.compile(r"[: ]+")
         auxv = dict([new_auxv(a, pattern) for a in auxv.splitlines()])
-        return not eval(self.auxv)
+        if eval(self.auxv):
+            return None
+
+        return "the auxv condition doesn't hold here"
 
     def skip_test_arch(self, myarch):
         # If architecture not set always run test
         if self.arch == '':
-            # log.warning("test for arch %s is ok" % myarch)
-            return False
+            return None
 
         # Allow multiple values in assignment separated by ','
         arch_list = self.arch.split(',')

@@ -468,24 +477,23 @@ class Test(object):
             arch_list[0] = arch_list[0][1:]
             log.warning("excluded architecture list %s", arch_list)
             for arch_item in arch_list:
-                # log.warning("test for %s arch is %s" % (arch_item, myarch))
                 if arch_item == myarch:
-                    return True
-            return False
+                    return "arch = %s, machine = %s" % (self.arch, myarch)
+            return None
 
         for arch_item in arch_list:
-            # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch))
             if arch_item == myarch:
-                return False
-        return True
+                return None
+
+        return "arch = %s, machine = %s" % (self.arch, myarch)
 
     def skip_test_requires(self):
         for requirement in filter(None, map(str.strip, self.requires.split(','))):
             if requirement == 'core-pmu' and not core_pmu_available():
                 log.warning("test limitation 'requires %s'", requirement)
-                return True
+                return "needs a core PMU, none here"
 
-        return False
+        return None
 
     def restore_sample_rate(self, value=10000):
         try:

@@ -529,20 +537,36 @@ class Test(object):
     def run_cmd(self, tempdir):
         _junk1, _junk2, _junk3, _junk4, myarch = (os.uname())
 
-        if self.skip_test_arch(myarch):
-            raise Notest(self, myarch)
-
-        if self.skip_test_auxv():
-            raise Notest(self, "auxv skip")
-
-        if self.skip_test_kernel_since():
-            raise Notest(self, "old kernel skip")
-
-        if self.skip_test_kernel_until():
-            raise Notest(self, "new kernel skip")
-
-        if self.skip_test_requires():
-            raise Notest(self, "requirements skip")
+        arch = self.skip_test_arch(myarch)
+        if arch:
+            log.debug("  detail: the test file has arch = %s, the machine reports %s",
+                     self.arch, myarch)
+            raise Notest(self, arch)
+
+        auxv = self.skip_test_auxv()
+        if auxv:
+            log.debug("  detail: the auxv condition %s doesn't hold, the bits come "
+                     "from the LD_SHOW_AUXV=1 output", self.auxv)
+            raise Notest(self, auxv)
+
+        kernel = self.skip_test_kernel_since()
+        if kernel:
+            log.debug("  detail: the test file's kernel_since = %d.%d, this kernel is %s",
+                     self.kernel_since[0], self.kernel_since[1], platform.release())
+            raise Notest(self, kernel)
+
+        kernel = self.skip_test_kernel_until()
+        if kernel:
+            log.debug("  detail: the test file's kernel_until = %d.%d, this kernel is %s",
+                     self.kernel_until[0], self.kernel_until[1], platform.release())
+            raise Notest(self, kernel)
+
+        requirement = self.skip_test_requires()
+        if requirement:
+            log.debug("  detail: requires core-pmu, nothing countable here, check "
+                     "kernel.perf_event_paranoid and the PMU nodes under "
+                     "/sys/bus/event_source/")
+            raise Notest(self, requirement)
 
         self.restore_sample_rate()
         cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir,

@@ -552,10 +576,16 @@ class Test(object):
         log.info("  '%s' ret '%s', expected '%s'", cmd, str(ret), str(self.ret))
 
         if not data_equal(str(ret), str(self.ret)):
+            plain_cmd = "%s %s %s" % (self.perf, self.command,
+                                      self.args.split('>/dev/null')[0].rstrip())
             if self.test_ret:
                 raise Fail(self, "Perf exit code failure")
             else:
-                raise Unsup(self)
+                log.debug("  detail: '%s' exited with %d, the expectations want the "
+                         "workload's %s exit, so there are no attrs recorded to "
+                         "verify; this is normally a capability problem, run '%s' "
+                         "to see why", plain_cmd, ret, self.ret, plain_cmd)
+                raise Unsup(self, ret, str(self.ret))
 
     def drop_dummy_tracking_events(self):
         """

index 859df74e62efc4b1..d3a7f7efaec705ed 100644
@@ -8,7 +8,7 @@ perf-test - Runs sanity tests.
 SYNOPSIS
 --------
 [verse]
-'perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]'
+'perf test [<options>] [{list|requisites} [<test-name-fragment>]|[<test-name-fragments>|<test-numbers>]]'
 
 DESCRIPTION
 -----------

@@ -18,9 +18,31 @@ also will look for a directory with more tests in the form of scripts.
 To get a list of available tests use 'perf test list', specifying a test name
 fragment will show all tests that have it.
 
+To get a list of what the tests need, i.e. of their requisites (see below), use
+'perf test requisites', that takes the same test name fragments and numbers as
+'list'.
+
 To run just specific tests, inform test name fragments or the numbers obtained
 from 'perf test list'.
 
+REQUISITES
+----------
+Shell tests run perf, that maps ring buffers, so they are taken to need room
+in the per user budget set in kernel.perf_event_mlock_kb, shared by the tests
+running at the same time, that take turns using it.  Tests state what they
+need, or waive, in a comma separated list in the parens ending their
+description line, e.g.:
+
+	# perf stat tests (no_mlock)
+
+"exclusive" is a catch-all: the test can't run alongside any other one, so
+it runs alone, in sequence, and implies every other requisite.  "no_mlock"
+waives the default, for tests that don't map ring buffers.  More keywords
+are to come, each stating what a test needs, till the catch-all isn't needed
+anymore.
+
+Use 'perf test requisites' to list what each test needs.
+
 OPTIONS
 -------
 -s::

@@ -36,8 +58,8 @@ OPTIONS
 
 -S::
 --sequential::
-	Run all tests one after the other. By default "exclusive"
-	tests are run sequentially, but other tests are run in
+	Run all tests one after the other. By default the tests asking to be
+	"exclusive" (see REQUISITES) run sequentially, but other tests run in
 	parallel to speed execution.
 
 -r::

index dbef5b6c4e43c857..4d37d11f674c5bd5 100644
@@ -85,6 +85,7 @@ FEATURE_TESTS_BASIC :=                  \
         libcpupower                     \
         pthread-attr-setaffinity-np     \
         pthread-barrier     		\
+        pthread-mutex-robust		\
         reallocarray                    \
         stackprotector-all              \
         timerfd                         \

index 62f9cbf3dee97936..10340a5372242e05 100644
@@ -41,6 +41,7 @@ FILES=                                          \
          $(foreach arch,$(LIBUNWIND_ARCHS),test-libunwind-$(arch).bin test-libunwind-debug-frame-$(arch).bin) \
          test-pthread-attr-setaffinity-np.bin   \
          test-pthread-barrier.bin		\
+         test-pthread-mutex-robust.bin		\
          test-stackprotector-all.bin            \
          test-timerfd.bin                       \
          test-babeltrace2-ctf-writer.bin        \

@@ -128,6 +129,9 @@ $(OUTPUT)test-pthread-attr-setaffinity-np.bin:
 $(OUTPUT)test-pthread-barrier.bin:
 	$(BUILD) -lpthread
 
+$(OUTPUT)test-pthread-mutex-robust.bin:
+	$(BUILD) -lpthread
+
 $(OUTPUT)test-stackprotector-all.bin:
 	$(BUILD) -fstack-protector-all
 

index cafc7be79643b26c..b4764f69f47f4d8c 100644
@@ -417,6 +417,10 @@ ifeq ($(feature-pthread-barrier), 1)
   CFLAGS += -DHAVE_PTHREAD_BARRIER
 endif
 
+ifeq ($(feature-pthread-mutex-robust), 1)
+  CFLAGS += -DHAVE_PTHREAD_MUTEX_ROBUST
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)

index e629fe0e8463d6cc..c827e613fc66ee0f 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# DRM PMU
+# DRM PMU (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 9f6e590f6437b2d9..84d6126bf94d1e61 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf ftrace tests
+# perf ftrace tests (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index d0eb99753f477f57..e3674cc52b30983f 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf kallsyms tests
+# perf kallsyms tests (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 err=0

index 14a03e0290ed1b4d..d4a0b04154d636f0 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf list tests
+# perf list tests (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index f13eb0a75b76ef5a..4ede9d701630c719 100755
@@ -1,5 +1,5 @@
 #!/bin/sh
-# perf sched stats tests
+# perf sched stats tests (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index c40e5f3f0825b051..43bdd693076b408c 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# Add vfs_getname probe to get syscall args filenames
+# Add vfs_getname probe to get syscall args filenames (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 # Arnaldo Carvalho de Melo <[email protected]>, 2017
 

index 2d6017d5dd9d9eab..ece4d306869ae48e 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# 'import perf' in python
+# 'import perf' in python (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 # Just test if we can load the python binding.
 set -e

index a4bdf2673d43ccc0..2050478e3f1a682f 100755
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Validate CPU and domain pairing in perf sched stats snapshots
+# Validate CPU and domain pairing in perf sched stats snapshots (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index a5b34c42e8d72aff..8beb6c674d055a52 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat CSV output linter
+# perf stat CSV output linter (no_mlock)
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Tests various perf stat CSV output commands for the
 # correct number of fields and the CSV separator set to ','.

index 9a4353db3825ede9..6d8beb88fb6f300a 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat csv summary test
+# perf stat csv summary test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index b5dec6b6da369382..f5c6fa30d8db38d1 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat events uniquifying
+# perf stat events uniquifying (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 4969ad70b67b6196..cbf7a4ffd7e8ab4f 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat JSON output linter
+# perf stat JSON output linter (no_mlock)
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Checks various perf stat JSON output commands for the
 # correct number of fields.

index cabbbf17c662df23..7a58e1507ce27957 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat metrics (shadow stat) test
+# perf stat metrics (shadow stat) test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 64c2b81f02deb18b..b915656a20f69d68 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat STD output linter
+# perf stat STD output linter (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 # Tests various perf stat STD output commands for
 # default event and metricgroup

index 1f5d4cc05807a247..ac9e031831daca9c 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat tests
+# perf stat tests (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 81bc7070b5ab0d5c..074a437da0ae3dce 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf all metricgroups test
+# perf all metricgroups test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 ParanoidAndNotRoot()

index df5fa27b21ae28d8..9d0d4b8a217e6730 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf all metrics test
+# perf all metrics test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 ParanoidAndNotRoot()

index c08c186af2c42e84..78d8006fb729c8f4 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf all libpfm4 events test
+# perf all libpfm4 events test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 if perf version --build-options | grep HAVE_LIBPFM | grep -q OFF

index febe3af0644157f3..d1b4632c17a3e8e1 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat --bpf-counters --for-each-cgroup test
+# perf stat --bpf-counters --for-each-cgroup test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 0728f48f21fa971d..75b8e01d11cc7ff3 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf stat metrics --for-each-cgroup test
+# perf stat metrics --for-each-cgroup test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 0982f6b9737a780f..3e073a0e5b9f9b99 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf metrics value validation
+# perf metrics value validation (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 shelldir=$(dirname "$0")

index 83048474710d2857..a235539c01767ee5 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# perf script ilist and perf list --tui test
+# perf script ilist and perf list --tui test (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e

index 6cb376c92e2f13a7..d1571a20f4683d73 100755
@@ -1,6 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
-# stat-cpi python test
+# stat-cpi python test (no_mlock)
 
 set -e
 

index 38a29e646906e3aa..2a3e8a00c48b7d39 100755
@@ -1,6 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
-# perf test junit XML output validation
+# perf test junit XML output validation (no_mlock)
 
 set -e
 

index 33bf36c4037e45ae..0a02ff9b86d6f326 100755
@@ -1,5 +1,5 @@
 #!/bin/bash
-# test perf probe of function from different CU
+# test perf probe of function from different CU (no_mlock)
 # SPDX-License-Identifier: GPL-2.0
 
 set -e