perf tests hwmon_pmu: Use PRIu64 + (u64) cast for a __u64 field to work more widely
PATCH 1/1 perf tests hwmon_pmu: Use PRIu64 + (u64) cast for a __u64 field to work more widely
While testing perf with an updated Debian experimental cross compiler (gcc version 14.2.0 (Debian 14.2.0-13)) this started failing:
In file included from tests/hwmon_pmu.c:12:
tests/hwmon_pmu.c: In function 'do_test':
tests/hwmon_pmu.c:199:34: error: format '%lld' expects argument of type 'long long int', but argument 7 has type '__u64' {aka 'long unsigned int'} [-Werror=format=]
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/git/perf-7.1.0-rc5/tools/perf/util/debug.h:20:21: note: in definition of macro 'pr_fmt'
20 | #define pr_fmt(fmt) fmt
| ^~~
tests/hwmon_pmu.c:199:25: note: in expansion of macro 'pr_debug'
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ^~~~~~~~
tests/hwmon_pmu.c:199:79: note: format string is defined here
199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n",
| ~~~^
| |
| long long int
| %ld LD /tmp/build/perf/util/intel-pt-decoder/perf-util-in.o
The usual make that %lld a PRIu64 (since arg7 is evsel->core.attr.config, which is a __u64) but then on Fedora 44 (gcc version 16.1.1 20260515 (Red Hat 16.1.1-2)) it ends up with:
In file included from tests/hwmon_pmu.c:13:
tests/hwmon_pmu.c: In function ‘do_test’:
tests/hwmon_pmu.c:200:34: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 7 has type ‘__u64’ {aka ‘long long unsigned int’} [-Werror=format=]
200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/acme/git/perf-tools-next2/tools/perf/util/debug.h:20:21: note: in definition of macro ‘pr_fmt’
20 | #define pr_fmt(fmt) fmt
| ^~~
tests/hwmon_pmu.c:200:25: note: in expansion of macro ‘pr_debug’
200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n",
| ^~~~~~~~cc1: all warnings being treated as errors
So the way to satisfy both compilers is to also add a (u64) cast to arg7.
--- tools/perf/tests/hwmon_pmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
tools/perf/tests/hwmon_pmu.c +3 -2
@@ -2,6 +2,7 @@#include "hwmon_pmu.h" #include <errno.h> +#include <inttypes.h> #include <fcntl.h> #include <linux/compiler.h>
@@ -196,9 +197,9 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)continue ;if (evsel->core.attr.config != (u64 )test_events[i].key.type_and_num) { -pr_debug ("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n" , +pr_debug ("FAILED %s:%d Unexpected config for '%s', %" PRIu64" != %ld\n" , __FILE__, __LINE__, str, - evsel->core.attr.config, + (u64 )evsel->core.attr.config, test_events[i].key.type_and_num); ret =TEST_FAIL ; goto out;
Signature · 1 line
2.54.0
Ian Rogers
reviewerQuoted 38 lines · Arnaldo Carvalho de Melo
While testing perf with an updated Debian experimental cross compiler (gcc version 14.2.0 (Debian 14.2.0-13)) this started failing:
In file included from
tests/hwmon_pmu.c:12:
tests/hwmon_pmu.c: In function 'do_test':
tests/hwmon_pmu.c:199:34: error: format '%lld' expects argument of type 'long long int', but argument 7 has type '__u64' {aka 'long unsigned int'} [-Werror=format=]199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /git/perf-7.1.0-rc5/tools/perf/util/debug.h:20:21: note: in definition of macro 'pr_fmt' 20 | #define pr_fmt(fmt) fmt | ^~~ tests/hwmon_pmu.c:199:25: note: in expansion of macro 'pr_debug' 199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ^~~~~~~~ tests/hwmon_pmu.c:199:79: note: format string is defined here 199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ~~~^ | | | long long int | %ldLD
/tmp/build/perf/util/intel-pt-decoder/perf-util-in.oThe usual make that %lld a PRIu64 (since arg7 is
evsel->core.attr.config, which is a__u64) but then on Fedora 44 (gcc version 16.1.1 20260515 (Red Hat 16.1.1-2)) it ends up with:In file included from
tests/hwmon_pmu.c:13:
tests/hwmon_pmu.c: In function ‘do_test’:
tests/hwmon_pmu.c:200:34: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 7 has type ‘__u64’ {aka ‘long long unsigned int’} [-Werror=format=]200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /home/acme/git/perf-tools-next2/tools/perf/util/debug.h:20:21: note: in definition of macro ‘pr_fmt’ 20 | #define pr_fmt(fmt) fmt | ^~~ tests/hwmon_pmu.c:200:25: note: in expansion of macro ‘pr_debug’ 200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n", | ^~~~~~~~
Quoted 4 lines
cc1: all warnings being treated as errors
So the way to satisfy both compilers is to also add a (u64) cast to arg7.
As the inttypes.h definitions match stdint.h would it make more sense to use uint64_t for the cast?
Thanks,
Ian
Quoted 32 lines
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>--- tools/perf/tests/hwmon_pmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)tools/perf/tests/hwmon_pmu.c +3
-3@@ -2,6 +2,7 @@#include "hwmon_pmu.h" #include <errno.h> +#include <inttypes.h> #include <fcntl.h> #include <linux/compiler.h> @@ -196,9 +197,9 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)continue ;if (evsel->core.attr.config != (u64 )test_events[i].key.type_and_num) { -pr_debug ("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n" , +pr_debug ("FAILED %s:%d Unexpected config for '%s', %" PRIu64" != %ld\n" , __FILE__, __LINE__, str, - evsel->core.attr.config, + (u64 )evsel->core.attr.config, test_events[i].key.type_and_num); ret =TEST_FAIL ; goto out; --2.54.0
Quoted 42 lines · On Thu, 28 May 2026 12:55:45 -0700 Ian Rogers <[email protected]> wrote:
Quoted 40 lines · Arnaldo Carvalho de Melo
While testing perf with an updated Debian experimental cross compiler (gcc version 14.2.0 (Debian 14.2.0-13)) this started failing:
In file included from
tests/hwmon_pmu.c:12:
tests/hwmon_pmu.c: In function 'do_test':
tests/hwmon_pmu.c:199:34: error: format '%lld' expects argument of type 'long long int', but argument 7 has type '__u64' {aka 'long unsigned int'} [-Werror=format=]199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /git/perf-7.1.0-rc5/tools/perf/util/debug.h:20:21: note: in definition of macro 'pr_fmt' 20 | #define pr_fmt(fmt) fmt | ^~~ tests/hwmon_pmu.c:199:25: note: in expansion of macro 'pr_debug' 199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ^~~~~~~~ tests/hwmon_pmu.c:199:79: note: format string is defined here 199 | pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", | ~~~^ | | | long long int | %ldLD
/tmp/build/perf/util/intel-pt-decoder/perf-util-in.oThe usual make that %lld a PRIu64 (since arg7 is
evsel->core.attr.config, which is a__u64) but then on Fedora 44 (gcc version 16.1.1 20260515 (Red Hat 16.1.1-2)) it ends up with:In file included from
tests/hwmon_pmu.c:13:
tests/hwmon_pmu.c: In function ‘do_test’:
tests/hwmon_pmu.c:200:34: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 7 has type ‘__u64’ {aka ‘long long unsigned int’} [-Werror=format=]200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /home/acme/git/perf-tools-next2/tools/perf/util/debug.h:20:21: note: in definition of macro ‘pr_fmt’ 20 | #define pr_fmt(fmt) fmt | ^~~ tests/hwmon_pmu.c:200:25: note: in expansion of macro ‘pr_debug’ 200 | pr_debug("FAILED %s:%d Unexpected config for '%s', %" PRIu64 " != %ld\n", | ^~~~~~~~cc1: all warnings being treated as errors
Quoted 5 lines
Quoted 2 lines
So the way to satisfy both compilers is to also add a (u64) cast to arg7.
As the
inttypes.hdefinitions matchstdint.hwould it make more sense to useuint64_tfor the cast?
Or use (unsigned long long) and "%lld". Using PRIu64 and a cast is the worst of both worlds.
Where does the definition of __u64 come from?
#define __u64 @@
at the top of a file might give a clue.
I thought it was a Linux kernel type matching u64 - which is always 'unsigned long long'.
-- David
Quoted 37 lines
Thanks,
IanQuoted 32 lines
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>--- tools/perf/tests/hwmon_pmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)tools/perf/tests/hwmon_pmu.c +3
-3@@ -2,6 +2,7 @@#include "hwmon_pmu.h" #include <errno.h> +#include <inttypes.h> #include <fcntl.h> #include <linux/compiler.h> @@ -196,9 +197,9 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)continue ;if (evsel->core.attr.config != (u64 )test_events[i].key.type_and_num) { -pr_debug ("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n" , +pr_debug ("FAILED %s:%d Unexpected config for '%s', %" PRIu64" != %ld\n" , __FILE__, __LINE__, str, - evsel->core.attr.config, + (u64 )evsel->core.attr.config, test_events[i].key.type_and_num); ret =TEST_FAIL ; goto out; --2.54.0