[PATCH v3] perf test: Fix perf stat --bpf-counters on hybrid machines

[PATCH v3] perf test: Fix perf stat --bpf-counters on hybrid machines

[Namhyung Kim]

The test constantly fails on my Intel hybrid machine.  The issue was it
has two events in the output even if I only gave it one event.

  $ perf stat -e instructions -- perf test -w sqrtloop

   Performance counter stats for 'perf test -w sqrtloop':

         910,856,421      cpu_atom/instructions/                (28.05%)
      14,852,865,997      cpu_core/instructions/                (96.79%)

         1.014313341 seconds time elapsed

         1.004114000 seconds user
         0.008174000 seconds sys

Let's modify the awk script to add the values for each line and print
the total.  The variable 'i' has a number of input lines that have valid
output and variable 'c' has the sum of actual counter values.  That way
it should work on any platforms.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
v3) make sure to print numbers w/o thousand separators.
v2) handle '<not counted>' and '<not supported>'.

 tools/perf/tests/shell/stat_bpf_counters.sh | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index f43e28a136d3c9bc..35463358b273ce1c 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -41,8 +41,14 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
-	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
+	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | \
+				awk -v i=0 -v c=0 '/instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
+	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | \
+				awk -v i=0 -v c=0 '/instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
 	check_counts $base_instructions $bpf_instructions
 	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"
@@ -52,8 +58,14 @@ test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
 	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
-	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
-	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
+	base_instructions=$(echo "$stat_output"| \
+				awk -v i=0 -v c=0 '/base_instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
+	bpf_instructions=$(echo "$stat_output"| \
+				awk -v i=0 -v c=0 '/bpf_instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
 	check_counts $base_instructions $bpf_instructions
 	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"
-- 
2.53.0

Re: [PATCH v3] perf test: Fix perf stat --bpf-counters on hybrid machines

[Arnaldo Carvalho de Melo]

On Wed, Mar 18, 2026 at 11:45:13PM -0700, Namhyung Kim wrote:
> The test constantly fails on my Intel hybrid machine.  The issue was it
> has two events in the output even if I only gave it one event.
> 
>   $ perf stat -e instructions -- perf test -w sqrtloop
> 
>    Performance counter stats for 'perf test -w sqrtloop':
> 
>          910,856,421      cpu_atom/instructions/                (28.05%)
>       14,852,865,997      cpu_core/instructions/                (96.79%)
> 
>          1.014313341 seconds time elapsed
> 
>          1.004114000 seconds user
>          0.008174000 seconds sys
> 
> Let's modify the awk script to add the values for each line and print
> the total.  The variable 'i' has a number of input lines that have valid
> output and variable 'c' has the sum of actual counter values.  That way
> it should work on any platforms.

Still doesn't pass reliably for me, only once it did work:

⬢ [acme@toolbx perf-tools]$ git log --oneline -1
38415985abcdb64d (HEAD -> perf-tools, number/perf-tools, number/HEAD) perf test: Fix perf stat --bpf-counters on hybrid machines
⬢ [acme@toolbx perf-tools]$
logout
acme@x1:~/git/perf-tools$
acme@x1:~/git/perf-tools$
acme@x1:~/git/perf-tools$ sudo su -
root@x1:~# perf -v
perf version 7.0.rc4.g38415985abcd
root@x1:~# perf test 152
152: perf stat --bpf-counters test                                   : FAILED!
root@x1:~# set -o vi
root@x1:~# perf test -v 152
152: perf stat --bpf-counters test                                   : Ok
root@x1:~# perf test -v 152
--- start ---
test child forked, pid 1829364
Testing --bpf-counters The difference between 21947395146 and 16947118203 are greater than 20%.
---- end(-1) ----
152: perf stat --bpf-counters test                                   : FAILED!
root@x1:~# perf test -v 152
--- start ---
test child forked, pid 1829401
Testing --bpf-counters [Success]
Testing bpf event modifier The difference between 22461906845 and 17190344465 are greater than 20%.
---- end(-1) ----
152: perf stat --bpf-counters test                                   : FAILED!
root@x1:~# perf test -v 152
--- start ---
test child forked, pid 1829445
Testing --bpf-counters The difference between 24210793380 and 16852007232 are greater than 20%.
---- end(-1) ----
152: perf stat --bpf-counters test                                   : FAILED!
root@x1:~# perf test -v 152
--- start ---
test child forked, pid 1829481
Testing --bpf-counters The difference between 24293201069 and 17225814972 are greater than 20%.
---- end(-1) ----
152: perf stat --bpf-counters test                                   : FAILED!
root@x1:~# grep -m1 "model name" /proc/cpuinfo
model name	: 13th Gen Intel(R) Core(TM) i7-1365U
root@x1:~#

acme@x1:~/git/perf-tools$ uname -a
Linux x1 6.17.12-300.fc43.x86_64 #1 SMP PREEMPT_DYNAMIC Sat Dec 13 05:06:24 UTC 2025 x86_64 GNU/Linux
acme@x1:~/git/perf-tools$ 
 
> Reviewed-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> v3) make sure to print numbers w/o thousand separators.
> v2) handle '<not counted>' and '<not supported>'.
> 
>  tools/perf/tests/shell/stat_bpf_counters.sh | 20 ++++++++++++++++----
>  1 file changed, 16 insertions(+), 4 deletions(-)
> 
> diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
> index f43e28a136d3c9bc..35463358b273ce1c 100755
> --- a/tools/perf/tests/shell/stat_bpf_counters.sh
> +++ b/tools/perf/tests/shell/stat_bpf_counters.sh
> @@ -41,8 +41,14 @@ check_counts()
>  test_bpf_counters()
>  {
>  	printf "Testing --bpf-counters "
> -	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
> -	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
> +	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | \
> +				awk -v i=0 -v c=0 '/instructions/ { \
> +					if ($1 != "<not") { i++; c += $1 } \
> +				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
> +	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | \
> +				awk -v i=0 -v c=0 '/instructions/ { \
> +					if ($1 != "<not") { i++; c += $1 } \
> +				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
>  	check_counts $base_instructions $bpf_instructions
>  	compare_number $base_instructions $bpf_instructions
>  	echo "[Success]"
> @@ -52,8 +58,14 @@ test_bpf_modifier()
>  {
>  	printf "Testing bpf event modifier "
>  	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
> -	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
> -	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
> +	base_instructions=$(echo "$stat_output"| \
> +				awk -v i=0 -v c=0 '/base_instructions/ { \
> +					if ($1 != "<not") { i++; c += $1 } \
> +				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
> +	bpf_instructions=$(echo "$stat_output"| \
> +				awk -v i=0 -v c=0 '/bpf_instructions/ { \
> +					if ($1 != "<not") { i++; c += $1 } \
> +				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
>  	check_counts $base_instructions $bpf_instructions
>  	compare_number $base_instructions $bpf_instructions
>  	echo "[Success]"
> -- 
> 2.53.0

Re: [PATCH v3] perf test: Fix perf stat --bpf-counters on hybrid machines

[Ian Rogers]

On Sun, Mar 22, 2026 at 3:05 PM Arnaldo Carvalho de Melo
<acme@kernel.org> wrote:
>
> On Wed, Mar 18, 2026 at 11:45:13PM -0700, Namhyung Kim wrote:
> > The test constantly fails on my Intel hybrid machine.  The issue was it
> > has two events in the output even if I only gave it one event.
> >
> >   $ perf stat -e instructions -- perf test -w sqrtloop
> >
> >    Performance counter stats for 'perf test -w sqrtloop':
> >
> >          910,856,421      cpu_atom/instructions/                (28.05%)
> >       14,852,865,997      cpu_core/instructions/                (96.79%)
> >
> >          1.014313341 seconds time elapsed
> >
> >          1.004114000 seconds user
> >          0.008174000 seconds sys
> >
> > Let's modify the awk script to add the values for each line and print
> > the total.  The variable 'i' has a number of input lines that have valid
> > output and variable 'c' has the sum of actual counter values.  That way
> > it should work on any platforms.
>
> Still doesn't pass reliably for me, only once it did work:
>
> ⬢ [acme@toolbx perf-tools]$ git log --oneline -1
> 38415985abcdb64d (HEAD -> perf-tools, number/perf-tools, number/HEAD) perf test: Fix perf stat --bpf-counters on hybrid machines
> ⬢ [acme@toolbx perf-tools]$
> logout
> acme@x1:~/git/perf-tools$
> acme@x1:~/git/perf-tools$
> acme@x1:~/git/perf-tools$ sudo su -
> root@x1:~# perf -v
> perf version 7.0.rc4.g38415985abcd
> root@x1:~# perf test 152
> 152: perf stat --bpf-counters test                                   : FAILED!
> root@x1:~# set -o vi
> root@x1:~# perf test -v 152
> 152: perf stat --bpf-counters test                                   : Ok
> root@x1:~# perf test -v 152
> --- start ---
> test child forked, pid 1829364
> Testing --bpf-counters The difference between 21947395146 and 16947118203 are greater than 20%.
> ---- end(-1) ----
> 152: perf stat --bpf-counters test                                   : FAILED!
> root@x1:~# perf test -v 152
> --- start ---
> test child forked, pid 1829401
> Testing --bpf-counters [Success]
> Testing bpf event modifier The difference between 22461906845 and 17190344465 are greater than 20%.
> ---- end(-1) ----
> 152: perf stat --bpf-counters test                                   : FAILED!
> root@x1:~# perf test -v 152
> --- start ---
> test child forked, pid 1829445
> Testing --bpf-counters The difference between 24210793380 and 16852007232 are greater than 20%.
> ---- end(-1) ----
> 152: perf stat --bpf-counters test                                   : FAILED!
> root@x1:~# perf test -v 152
> --- start ---
> test child forked, pid 1829481
> Testing --bpf-counters The difference between 24293201069 and 17225814972 are greater than 20%.
> ---- end(-1) ----
> 152: perf stat --bpf-counters test                                   : FAILED!
> root@x1:~# grep -m1 "model name" /proc/cpuinfo
> model name      : 13th Gen Intel(R) Core(TM) i7-1365U
> root@x1:~#
>
> acme@x1:~/git/perf-tools$ uname -a
> Linux x1 6.17.12-300.fc43.x86_64 #1 SMP PREEMPT_DYNAMIC Sat Dec 13 05:06:24 UTC 2025 x86_64 GNU/Linux
> acme@x1:~/git/perf-tools$

So I think the real issue here is the multiplexing value, which I've
looked to fix with:
https://lore.kernel.org/lkml/20250716223924.825772-1-irogers@google.com/

I have a patch to switch to task-clock which is a software event with
a CPU mask of all online CPUs rather than the split seen on hybrid
machines. I'll send it in reply here.

Thanks,
Ian

> > Reviewed-by: Ian Rogers <irogers@google.com>
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > v3) make sure to print numbers w/o thousand separators.
> > v2) handle '<not counted>' and '<not supported>'.
> >
> >  tools/perf/tests/shell/stat_bpf_counters.sh | 20 ++++++++++++++++----
> >  1 file changed, 16 insertions(+), 4 deletions(-)
> >
> > diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
> > index f43e28a136d3c9bc..35463358b273ce1c 100755
> > --- a/tools/perf/tests/shell/stat_bpf_counters.sh
> > +++ b/tools/perf/tests/shell/stat_bpf_counters.sh
> > @@ -41,8 +41,14 @@ check_counts()
> >  test_bpf_counters()
> >  {
> >       printf "Testing --bpf-counters "
> > -     base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
> > -     bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
> > +     base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | \
> > +                             awk -v i=0 -v c=0 '/instructions/ { \
> > +                                     if ($1 != "<not") { i++; c += $1 } \
> > +                             } END { if (i > 0) printf "%.0f", c; else print "<not" }')
> > +     bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | \
> > +                             awk -v i=0 -v c=0 '/instructions/ { \
> > +                                     if ($1 != "<not") { i++; c += $1 } \
> > +                             } END { if (i > 0) printf "%.0f", c; else print "<not" }')
> >       check_counts $base_instructions $bpf_instructions
> >       compare_number $base_instructions $bpf_instructions
> >       echo "[Success]"
> > @@ -52,8 +58,14 @@ test_bpf_modifier()
> >  {
> >       printf "Testing bpf event modifier "
> >       stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
> > -     base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
> > -     bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
> > +     base_instructions=$(echo "$stat_output"| \
> > +                             awk -v i=0 -v c=0 '/base_instructions/ { \
> > +                                     if ($1 != "<not") { i++; c += $1 } \
> > +                             } END { if (i > 0) printf "%.0f", c; else print "<not" }')
> > +     bpf_instructions=$(echo "$stat_output"| \
> > +                             awk -v i=0 -v c=0 '/bpf_instructions/ { \
> > +                                     if ($1 != "<not") { i++; c += $1 } \
> > +                             } END { if (i > 0) printf "%.0f", c; else print "<not" }')
> >       check_counts $base_instructions $bpf_instructions
> >       compare_number $base_instructions $bpf_instructions
> >       echo "[Success]"
> > --
> > 2.53.0

[RFC PATCH v1] perf test: Fix perf stat --bpf-counters on hybrid machines

[Ian Rogers]

Events on hardware PMUs may open on >1 hardware PMU on hybrid
machines. Unfortunately multiplexing introduces a scaling issue as
reported in:
https://lore.kernel.org/lkml/20250716223924.825772-1-irogers@google.com/

Switch to using task-clock which as a software event runs on all CPUs
and has a single PMU.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/stat_bpf_counters.sh | 35 +++++++++++----------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index f43e28a136d3..58f7dc9692ac 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -5,6 +5,7 @@
 set -e
 
 workload="perf test -w sqrtloop"
+event=task-clock
 
 # check whether $2 is within +/- 20% of $1
 compare_number()
@@ -25,15 +26,15 @@ compare_number()
 
 check_counts()
 {
-	base_instructions=$1
-	bpf_instructions=$2
+	base_count=$(echo "$1"|sed -e 's/[^0-9]*\([0-9]*\).*/\1/')
+	bpf_count=$(echo "$2"|sed -e 's/[^0-9]*\([0-9]*\).*/\1/')
 
-	if [ "$base_instructions" = "<not" ]; then
-		echo "Skipping: instructions event not counted"
+	if [ "$base_count" = "<not" ]; then
+		echo "Skipping: $event event not counted"
 		exit 2
 	fi
-	if [ "$bpf_instructions" = "<not" ]; then
-		echo "Failed: instructions not counted with --bpf-counters"
+	if [ "$bpf_count" = "<not" ]; then
+		echo "Failed: $event not counted with --bpf-counters"
 		exit 1
 	fi
 }
@@ -41,29 +42,29 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
-	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
-	check_counts $base_instructions $bpf_instructions
-	compare_number $base_instructions $bpf_instructions
+	base_count=$(perf stat --no-big-num -e "$event" -- $workload 2>&1 | awk "/$event/ {print \$1}")
+	bpf_count=$(perf stat --no-big-num --bpf-counters -e "$event" -- $workload  2>&1 | awk "/$event/ {print \$1}")
+	check_counts "$base_count" "$bpf_count"
+	compare_number "$base_count" "$bpf_count"
 	echo "[Success]"
 }
 
 test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
-	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
-	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
-	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
-	check_counts $base_instructions $bpf_instructions
-	compare_number $base_instructions $bpf_instructions
+	stat_output=$(perf stat --no-big-num -e "$event/name=base_$event/,$event/name=bpf_$event/b" -- $workload 2>&1)
+	base_count=$(echo "$stat_output"| awk "/base_$event/ {print \$1}")
+	bpf_count=$(echo "$stat_output"| awk "/bpf_$event/ {print \$1}")
+	check_counts "$base_count" "$bpf_count"
+	compare_number "$base_count" "$bpf_count"
 	echo "[Success]"
 }
 
 # skip if --bpf-counters is not supported
-if ! perf stat -e instructions --bpf-counters true > /dev/null 2>&1; then
+if ! perf stat -e $event --bpf-counters true > /dev/null 2>&1; then
 	if [ "$1" = "-v" ]; then
 		echo "Skipping: --bpf-counters not supported"
-		perf --no-pager stat -e instructions --bpf-counters true || true
+		perf --no-pager stat -e $event --bpf-counters true || true
 	fi
 	exit 2
 fi
-- 
2.53.0.1018.g2bb0e51243-goog

Re: [RFC PATCH v1] perf test: Fix perf stat --bpf-counters on hybrid machines

[Ian Rogers]

On Mon, Mar 23, 2026 at 1:24 PM Ian Rogers <irogers@google.com> wrote:
>
> Events on hardware PMUs may open on >1 hardware PMU on hybrid
> machines. Unfortunately multiplexing introduces a scaling issue as
> reported in:
> https://lore.kernel.org/lkml/20250716223924.825772-1-irogers@google.com/
>
> Switch to using task-clock which as a software event runs on all CPUs
> and has a single PMU.
>
> Signed-off-by: Ian Rogers <irogers@google.com>

With hindsight, maybe the better thing to do is Namhyung's patch plus
the "--no-scale" option to `perf stat` to sidestep the scaling issue.
It'd be great to make this test not "(exclusive)", it shouldn't be
necessary. You can test for flakiness with the '-r' option to `perf
test` which takes a repeat count.

Thanks,
Ian

> ---
>  tools/perf/tests/shell/stat_bpf_counters.sh | 35 +++++++++++----------
>  1 file changed, 18 insertions(+), 17 deletions(-)
>
> diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
> index f43e28a136d3..58f7dc9692ac 100755
> --- a/tools/perf/tests/shell/stat_bpf_counters.sh
> +++ b/tools/perf/tests/shell/stat_bpf_counters.sh
> @@ -5,6 +5,7 @@
>  set -e
>
>  workload="perf test -w sqrtloop"
> +event=task-clock
>
>  # check whether $2 is within +/- 20% of $1
>  compare_number()
> @@ -25,15 +26,15 @@ compare_number()
>
>  check_counts()
>  {
> -       base_instructions=$1
> -       bpf_instructions=$2
> +       base_count=$(echo "$1"|sed -e 's/[^0-9]*\([0-9]*\).*/\1/')
> +       bpf_count=$(echo "$2"|sed -e 's/[^0-9]*\([0-9]*\).*/\1/')
>
> -       if [ "$base_instructions" = "<not" ]; then
> -               echo "Skipping: instructions event not counted"
> +       if [ "$base_count" = "<not" ]; then
> +               echo "Skipping: $event event not counted"
>                 exit 2
>         fi
> -       if [ "$bpf_instructions" = "<not" ]; then
> -               echo "Failed: instructions not counted with --bpf-counters"
> +       if [ "$bpf_count" = "<not" ]; then
> +               echo "Failed: $event not counted with --bpf-counters"
>                 exit 1
>         fi
>  }
> @@ -41,29 +42,29 @@ check_counts()
>  test_bpf_counters()
>  {
>         printf "Testing --bpf-counters "
> -       base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
> -       bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
> -       check_counts $base_instructions $bpf_instructions
> -       compare_number $base_instructions $bpf_instructions
> +       base_count=$(perf stat --no-big-num -e "$event" -- $workload 2>&1 | awk "/$event/ {print \$1}")
> +       bpf_count=$(perf stat --no-big-num --bpf-counters -e "$event" -- $workload  2>&1 | awk "/$event/ {print \$1}")
> +       check_counts "$base_count" "$bpf_count"
> +       compare_number "$base_count" "$bpf_count"
>         echo "[Success]"
>  }
>
>  test_bpf_modifier()
>  {
>         printf "Testing bpf event modifier "
> -       stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
> -       base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
> -       bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
> -       check_counts $base_instructions $bpf_instructions
> -       compare_number $base_instructions $bpf_instructions
> +       stat_output=$(perf stat --no-big-num -e "$event/name=base_$event/,$event/name=bpf_$event/b" -- $workload 2>&1)
> +       base_count=$(echo "$stat_output"| awk "/base_$event/ {print \$1}")
> +       bpf_count=$(echo "$stat_output"| awk "/bpf_$event/ {print \$1}")
> +       check_counts "$base_count" "$bpf_count"
> +       compare_number "$base_count" "$bpf_count"
>         echo "[Success]"
>  }
>
>  # skip if --bpf-counters is not supported
> -if ! perf stat -e instructions --bpf-counters true > /dev/null 2>&1; then
> +if ! perf stat -e $event --bpf-counters true > /dev/null 2>&1; then
>         if [ "$1" = "-v" ]; then
>                 echo "Skipping: --bpf-counters not supported"
> -               perf --no-pager stat -e instructions --bpf-counters true || true
> +               perf --no-pager stat -e $event --bpf-counters true || true
>         fi
>         exit 2
>  fi
> --
> 2.53.0.1018.g2bb0e51243-goog
>

Re: [RFC PATCH v1] perf test: Fix perf stat --bpf-counters on hybrid machines

[Namhyung Kim]

On Mon, Mar 23, 2026 at 01:26:11PM -0700, Ian Rogers wrote:
> On Mon, Mar 23, 2026 at 1:24 PM Ian Rogers <irogers@google.com> wrote:
> >
> > Events on hardware PMUs may open on >1 hardware PMU on hybrid
> > machines. Unfortunately multiplexing introduces a scaling issue as
> > reported in:
> > https://lore.kernel.org/lkml/20250716223924.825772-1-irogers@google.com/
> >
> > Switch to using task-clock which as a software event runs on all CPUs
> > and has a single PMU.
> >
> > Signed-off-by: Ian Rogers <irogers@google.com>
> 
> With hindsight, maybe the better thing to do is Namhyung's patch plus
> the "--no-scale" option to `perf stat` to sidestep the scaling issue.
> It'd be great to make this test not "(exclusive)", it shouldn't be
> necessary. You can test for flakiness with the '-r' option to `perf
> test` which takes a repeat count.

I think your fix is simpler and better. :)

Acked-by: Namhyung Kim <namhyung@kernel.org>

Thanks,
Namhyung

[PATCH v2] perf test: Fix perf stat --bpf-counters on hybrid machines

[Ian Rogers]

Events on hardware PMUs may open on >1 hardware PMU on hybrid
machines. Unfortunately multiplexing introduces a scaling issue as
reported in:
https://lore.kernel.org/lkml/20250716223924.825772-1-irogers@google.com/

Switch to using task-clock which as a software event runs on all CPUs
and has a single PMU.

For when hybrid event scaling is fixed, incorporate support for
combining hybrid counts as posted by Namhyung Kim in:
https://lore.kernel.org/lkml/20260319064513.9269-1-namhyung@kernel.org/

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
---
v1: https://lore.kernel.org/lkml/20260323202409.194123-1-irogers@google.com/
---
 tools/perf/tests/shell/stat_bpf_counters.sh | 55 ++++++++++++++-------
 1 file changed, 38 insertions(+), 17 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index f43e28a136d3..f8c24ccc7830 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -5,6 +5,24 @@
 set -e
 
 workload="perf test -w sqrtloop"
+event=task-clock
+
+extract_count()
+{
+	local target_event="$1"
+
+	awk -v target="$target_event" -v i=0 -v c=0 '
+	$0 ~ target {
+		i++;
+		c += $1
+	}
+	END {
+		if (i > 0)
+			printf "%.0f\n", c;
+		else
+			print "<not counted>"
+	}'
+}
 
 # check whether $2 is within +/- 20% of $1
 compare_number()
@@ -25,15 +43,15 @@ compare_number()
 
 check_counts()
 {
-	base_instructions=$1
-	bpf_instructions=$2
+	base_count=$1
+	bpf_count=$2
 
-	if [ "$base_instructions" = "<not" ]; then
-		echo "Skipping: instructions event not counted"
+	if [ "$base_count" = "<not counted>" ]; then
+		echo "Skipping: $event event not counted"
 		exit 2
 	fi
-	if [ "$bpf_instructions" = "<not" ]; then
-		echo "Failed: instructions not counted with --bpf-counters"
+	if [ "$bpf_count" = "<not counted>" ]; then
+		echo "Failed: $event not counted with --bpf-counters"
 		exit 1
 	fi
 }
@@ -41,29 +59,32 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
-	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
-	check_counts $base_instructions $bpf_instructions
-	compare_number $base_instructions $bpf_instructions
+	base_count=$(perf stat --no-big-num -e "$event" -- $workload 2>&1 \
+          | extract_count "$event")
+	bpf_count=$(perf stat --no-big-num --bpf-counters -e "$event" -- $workload  2>&1 \
+          | extract_count "$event")
+	check_counts "$base_count" "$bpf_count"
+	compare_number "$base_count" "$bpf_count"
 	echo "[Success]"
 }
 
 test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
-	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
-	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
-	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
-	check_counts $base_instructions $bpf_instructions
-	compare_number $base_instructions $bpf_instructions
+	stat_output=$(perf stat --no-big-num \
+          -e "$event/name=base_$event/,$event/name=bpf_$event/b" -- $workload 2>&1)
+	base_count=$(echo "$stat_output" | extract_count "base_$event")
+	bpf_count=$(echo "$stat_output"|  extract_count "bpf_$event")
+	check_counts "$base_count" "$bpf_count"
+	compare_number "$base_count" "$bpf_count"
 	echo "[Success]"
 }
 
 # skip if --bpf-counters is not supported
-if ! perf stat -e instructions --bpf-counters true > /dev/null 2>&1; then
+if ! perf stat -e "$event" --bpf-counters true > /dev/null 2>&1; then
 	if [ "$1" = "-v" ]; then
 		echo "Skipping: --bpf-counters not supported"
-		perf --no-pager stat -e instructions --bpf-counters true || true
+		perf --no-pager stat -e "$event" --bpf-counters true || true
 	fi
 	exit 2
 fi
-- 
2.53.0.1018.g2bb0e51243-goog