perf record: fix fallback to cpu-clock on ppc
PATCH 1/2 perf record: fix fallback to cpu-clock on ppc
perf-record on PPC is not falling back to cpu-clock:
$ perf record -ag -fo /tmp/perf.data -- sleep 1
Error: sys_perf_event_open() syscall returned with 6 (No such device or address). /bin/dmesg may provide additional information.
Fatal: No CONFIG_PERF_EVENTS=y kernel support configured?
The problem is that until 2.6.37 (behavior changed with commit b0a873e) perf on PPC returns ENXIO when hw_perf_event_init() fails. With this patch we get the expected behavior:
$ perf record -ag -fo /tmp/perf.data -v -- sleep 1 Old kernel, cannot exclude guest or host samples. The cycles event is not supported, trying to fall back to cpu-clock-ticks [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.151 MB /tmp/perf.data (~6592 samples) ]
--- tools/perf/builtin-record.c | 8 ++++++-- 1 files changed, 6 insertions(+), 2 deletions(-)
tools/perf/builtin-record.c +6 -2
@@ -242,9 +242,13 @@ try_again:/* * If it's cycles then fall back to hrtimer * based cpu-clock-tick sw counter, which -* is always available even if no PMU support: +* is always available even if no PMU support. +* +* PPC returns ENXIO until 2.6.37 (behavior changed +* with commit b0a873e). */ -if (err ==ENOENT && attr->type ==PERF_TYPE_HARDWARE +if ((err ==ENOENT || err ==ENXIO ) + && attr->type ==PERF_TYPE_HARDWARE && attr->config ==PERF_COUNT_HW_CPU_CYCLES ) {if (verbose)
Signature · 1 line
1.7.5.4
[tip:perf/core] perf record: Fix fallback to cpu-clock on ppc
Commit-ID: 028d455b12719a48b1c4b51ce07a074135726f8f Gitweb: http://git.kernel.org/tip/028d455b12719a48b1c4b51ce07a074135726f8f Author: David Ahern <[email protected]> AuthorDate: Tue, 8 May 2012 09:28:57 -0600 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Wed, 9 May 2012 11:57:29 -0300
perf record: Fix fallback to cpu-clock on ppc
perf-record on PPC is not falling back to cpu-clock:
$ perf record -ag -fo /tmp/perf.data -- sleep 1
Error: sys_perf_event_open() syscall returned with 6 (No such device or address). /bin/dmesg may provide additional information.
Fatal: No CONFIG_PERF_EVENTS=y kernel support configured?
The problem is that until 2.6.37 (behavior changed with commit b0a873e) perf on PPC returns ENXIO when hw_perf_event_init() fails. With this patch we get the expected behavior:
$ perf record -ag -fo /tmp/perf.data -v -- sleep 1 Old kernel, cannot exclude guest or host samples. The cycles event is not supported, trying to fall back to cpu-clock-ticks [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.151 MB /tmp/perf.data (~6592 samples) ]
--- tools/perf/builtin-record.c | 8 ++++++-- 1 files changed, 6 insertions(+), 2 deletions(-)
tools/perf/builtin-record.c +6 -2
@@ -242,9 +242,13 @@ try_again:/* * If it's cycles then fall back to hrtimer * based cpu-clock-tick sw counter, which -* is always available even if no PMU support: +* is always available even if no PMU support. +* +* PPC returns ENXIO until 2.6.37 (behavior changed +* with commit b0a873e). */ -if (err ==ENOENT && attr->type ==PERF_TYPE_HARDWARE +if ((err ==ENOENT || err ==ENXIO ) + && attr->type ==PERF_TYPE_HARDWARE && attr->config ==PERF_COUNT_HW_CPU_CYCLES ) {if (verbose)