linux-stable.git/tools/perf/util/expr.y, branch v6.4

perf metric: Change divide by zero and !support events behavior

2023-05-10T15:35:02+00:00

Division by zero causes expression parsing to fail and no metric to be
generated. This can mean for short running benchmarks metrics are not
shown. Change the behavior to make the value nan, which gets shown like:

'''
$ perf stat -M TopdownL2 true

 Performance counter stats for 'true':

         1,031,492      INST_RETIRED.ANY                 #      nan %  tma_fetch_bandwidth
                                                  #      nan %  tma_heavy_operations
                                                  #      nan %  tma_light_operations
            29,304      CPU_CLK_UNHALTED.REF_XCLK        #      nan %  tma_fetch_latency
                                                  #      nan %  tma_branch_mispredicts
                                                  #      nan %  tma_machine_clears
                                                  #      nan %  tma_core_bound
                                                  #      nan %  tma_memory_bound
         2,658,319      IDQ_UOPS_NOT_DELIVERED.CORE
            11,167      EXE_ACTIVITY.BOUND_ON_STORES
           262,058      EXE_ACTIVITY.1_PORTS_UTIL
           BR_MISP_RETIRED.ALL_BRANCHES                                            (0.00%)
           INT_MISC.RECOVERY_CYCLES_ANY                                            (0.00%)
           CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE                                        (0.00%)
           CPU_CLK_UNHALTED.THREAD                                                 (0.00%)
           UOPS_RETIRED.RETIRE_SLOTS                                               (0.00%)
           CYCLE_ACTIVITY.STALLS_MEM_ANY                                           (0.00%)
           UOPS_RETIRED.MACRO_FUSED                                                (0.00%)
           IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE                                        (0.00%)
           EXE_ACTIVITY.2_PORTS_UTIL                                               (0.00%)
           CYCLE_ACTIVITY.STALLS_TOTAL                                             (0.00%)
           MACHINE_CLEARS.COUNT                                                    (0.00%)
           UOPS_ISSUED.ANY                                                         (0.00%)

       0.002864879 seconds time elapsed

       0.003012000 seconds user
       0.000000000 seconds sys
'''

When events aren't supported a count of 0 can be confusing and make
metrics look meaningful. Change these to be nan also which, with the
next change, gets shown like:

'''
$ perf stat true
 Performance counter stats for 'true':

              1.25 msec task-clock:u                     #    0.387 CPUs utilized
                 0      context-switches:u               #    0.000 /sec
                 0      cpu-migrations:u                 #    0.000 /sec
                46      page-faults:u                    #   36.702 K/sec
           255,942      cycles:u                         #    0.204 GHz                         (88.66%)
           123,046      instructions:u                   #    0.48  insn per cycle
            28,301      branches:u                       #   22.580 M/sec
             2,489      branch-misses:u                  #    8.79% of all branches
             4,719      CPU_CLK_UNHALTED.REF_XCLK:u      #    3.765 M/sec
                                                  #      nan %  tma_frontend_bound
                                                  #      nan %  tma_retiring
                                                  #      nan %  tma_backend_bound
                                                  #      nan %  tma_bad_speculation
           344,855      IDQ_UOPS_NOT_DELIVERED.CORE:u    #  275.147 M/sec
         INT_MISC.RECOVERY_CYCLES_ANY:u
           CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u                                        (0.00%)
           CPU_CLK_UNHALTED.THREAD:u                                               (0.00%)
           UOPS_RETIRED.RETIRE_SLOTS:u                                             (0.00%)
           UOPS_ISSUED.ANY:u                                                       (0.00%)

       0.003238142 seconds time elapsed

       0.000000000 seconds user
       0.003434000 seconds sys
'''

Ensure that nan metric values are quoted as nan isn't a valid number
in JSON.

Signed-off-by: Ian Rogers 
Tested-by: Kan Liang 
Cc: Adrian Hunter 
Cc: Ahmad Yasin 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Athira Rajeev 
Cc: Caleb Biggers 
Cc: Edward Baker 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kang Minchul 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Rob Herring 
Cc: Samantha Alt 
Cc: Stephane Eranian 
Cc: Sumanth Korikkar 
Cc: Suzuki Poulouse 
Cc: Thomas Richter 
Cc: Tiezhu Yang 
Cc: Weilin Wang 
Cc: Xing Zhengjun 
Cc: Yang Jihong 
Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: More explicit NAN handling

2023-02-19T11:06:59+00:00

Comparison and logical operations on NAN won't ensure the result is
NAN. Ensure NANs are propogated so that threshold expressions like
"tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15" don't yield a
number when the components are NAN.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Alexandre Torgue 
Cc: Andrii Nakryiko 
Cc: Athira Rajeev 
Cc: Caleb Biggers 
Cc: Eduard Zingerman 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jing Zhang 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Maxime Coquelin 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Sean Christopherson 
Cc: Stephane Eranian 
Cc: Suzuki Poulouse 
Cc: Xing Zhengjun 
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Link: https://lore.kernel.org/r/20230219092848.639226-38-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Allow a double if expression

2022-10-06T11:03:52+00:00

Some TMA metrics have double if expressions like:

  ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) if #core_wide < 1 else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD

This currently fails to parse as the left hand side if expression needs
to be in parentheses. By allowing the if expression to have a right hand
side that is an if expression we can parse the expression above, with
left to right evaluation order that matches languages like Python.

Signed-off-by: Ian Rogers 
Cc: Ahmad Yasin 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Caleb Biggers 
Cc: Florian Fischer 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Kshipra Bopardikar 
Cc: Mark Rutland 
Cc: Miaoqian Lin 
Cc: Namhyung Kim 
Cc: Perry Taylor 
Cc: Peter Zijlstra 
Cc: Samantha Alt 
Cc: Stephane Eranian 
Cc: Thomas Richter 
Cc: Xing Zhengjun 
Link: https://lore.kernel.org/r/20221004021612.325521-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Add source_count for aggregating events

2021-11-13T21:11:50+00:00

Events like uncore_imc/cas_count_read/ on Skylake open multiple events
and then aggregate in the metric leader. To determine the average value
per event the number of these events is needed. Add a source_count
function that returns this value by counting the number of events with
the given metric leader. For most events the value is 1 but for
uncore_imc/cas_count_read/ it can yield values like 6.

Add a generic test, but manually tested with a test metric that uses
the function.

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Madhavan Srinivasan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul A . Clarke 
Cc: Peter Zijlstra 
Cc: Riccardo Mancini 
Cc: Song Liu 
Cc: Wan Jiabing 
Cc: Yury Norov 
Link: https://lore.kernel.org/r/20211111002109.194172-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Move ID handling to its own function

2021-11-13T21:11:50+00:00

This will facilitate sharing in a follow-on change.

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Madhavan Srinivasan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul A . Clarke 
Cc: Peter Zijlstra 
Cc: Riccardo Mancini 
Cc: Song Liu 
Cc: Wan Jiabing 
Cc: Yury Norov 
Link: https://lore.kernel.org/r/20211111002109.194172-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Add literal values starting with #

2021-11-13T21:11:50+00:00

It is useful to have literal values for constants relating to
topologies, SMT, etc. Make the parsing of literals shared code and add a
lookup function. Move #smt_on to this function.

Signed-off-by: Ian Rogers 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Madhavan Srinivasan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul A . Clarke 
Cc: Peter Zijlstra 
Cc: Riccardo Mancini 
Cc: Song Liu 
Cc: Wan Jiabing 
Cc: Yury Norov 
Link: https://lore.kernel.org/r/20211111002109.194172-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf metric: Modify resolution and recursion check

2021-10-20T13:35:33+00:00

Modify resolution. Rather than resolving a list of metrics, resolve a
metric immediately after it is added.

This simplifies knowing the root of the metric's tree so that IDs may be
associated with it.

A bug in the current implementation is that all the IDs were placed on
the first metric in a metric group.

Rather than maintain data on IDs' parents to detect cycles, maintain
a list of visited metrics and detect cycles if the same metric is
visited twice.

Only place the root metric onto the list of metrics.

Signed-off-by: Ian Rogers 
Acked-by: Andi Kleen 
Cc: Adrian Hunter 
Cc: Alexander Antonov 
Cc: Alexander Shishkin 
Cc: Andrew Kilroy 
Cc: Andrew Morton 
Cc: Changbin Du 
Cc: Denys Zagorui 
Cc: Fabian Hemmer 
Cc: Felix Fietkau 
Cc: Heiko Carstens 
Cc: Ingo Molnar 
Cc: Jacob Keller 
Cc: Jiapeng Chong 
Cc: Jin Yao 
Cc: Jiri Olsa 
Cc: Joakim Zhang 
Cc: John Garry 
Cc: Kajol Jain 
Cc: Kan Liang 
Cc: Kees Kook 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Nicholas Fraser 
Cc: Nick Desaulniers 
Cc: Paul Clarke 
Cc: Peter Zijlstra 
Cc: Riccardo Mancini 
Cc: Sami Tolvanen 
Cc: ShihCheng Tu 
Cc: Song Liu 
Cc: Stephane Eranian 
Cc: Sumanth Korikkar 
Cc: Thomas Richter 
Cc: Wan Jiabing 
Cc: Zhen Lei 
Link: https://lore.kernel.org/r/20211015172132.1162559-10-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf metric: Avoid events for an 'if' constant result

2021-09-29T16:51:04+00:00

For a metric like:

  CONST if expr else CONST

if the values of CONST are identical then expr doesn't need evaluating,
and events, in order to compute a result.

Signed-off-by: Ian Rogers 
Tested-by: John Garry 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: Jin Yao 
Cc: Kajol Jain 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul Clarke 
Cc: Peter Zijlstra 
Cc: Sandeep Dasgupta 
Cc: Stephane Eranian 
Link: https://lore.kernel.org/r/20210923074616.674826-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf metric: Don't compute unused events

2021-09-29T16:51:04+00:00

For a metric like:

  EVENT1 if #smt_on else EVENT2

currently EVENT1 and EVENT2 will be measured and then when the metric is
reported EVENT1 or EVENT2 will be printed depending on the value from
smt_on() during the expr parsing. Computing both events is unnecessary and
can lead to multiplexing as discussed in this thread:

  https://lore.kernel.org/lkml/20201110100346.2527031-1-irogers@google.com/

If the input is constant to certain operators like:

 IDS1 if CONST else IDS2

then the result will be either IDS1 or IDS2 depending on CONST (which
may be evaluated from an entire expression), and so IDS1 or IDS2 may
be discarded avoiding events from being programmed.

Signed-off-by: Ian Rogers 
Tested-by: John Garry 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: Jin Yao 
Cc: Kajol Jain 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul Clarke 
Cc: Peter Zijlstra 
Cc: Sandeep Dasgupta 
Cc: Stephane Eranian 
Link: https://lore.kernel.org/r/20210923074616.674826-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf expr: Propagate constants for binary operations

2021-09-29T16:51:04+00:00

When we're computing ID values, if we have constant values then compute
the constant result. For example:

  1 + 2

Previously .val would be set to BOTTOM by union_expr, meaning that
all values are possible. With this change .val is set to 3.

Later changes will use the constant values to hopefully eliminate ID
values that don't need to be computed.

Signed-off-by: Ian Rogers 
Tested-by: John Garry 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Ingo Molnar 
Cc: Jin Yao 
Cc: Kajol Jain 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Paul Clarke 
Cc: Peter Zijlstra 
Cc: Sandeep Dasgupta 
Cc: Stephane Eranian 
Link: https://lore.kernel.org/r/20210923074616.674826-12-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo