perf intel-pt: Better support for perf record --cpu
Adrian Hunter
reviewercover perf intel-pt: Better support for perf record --cpu
Hi
Here are V1 patches to support capturing Intel PT sideband events such as mmap, task, context switch, text poke etc, on every CPU even when tracing selected user_requested_cpus. That is, when using the perf record -C or
--cpu option.
This is needed for:
1. text poke: a text poke on any CPU affects all CPUs
2. tracing user space: a user space process can migrate between CPUs so mmap events that happen on a different CPU can be needed to decode a user_requested_cpus CPU.
For example:
Trace on CPU 1:
perf record --kcore -C 1 -e intel_pt// &
Start a task on CPU 0:
taskset 0x1 testprog &
Migrate it to CPU 1:
taskset -p 0x2 <testprog pid>
Stop tracing:
kill %1
Prior to these changes there will be errors decoding testprog in userspace because the comm and mmap events for testprog will not have been captured.
There is quite a bit of preparation:
The first patch is a small Intel PT test for system-wide side band. The test fails before the patches are applied, passed afterwards.
perf intel-pt: Add a test for system-wide side band [new in V1]
The next 5 patches stop auxtrace mixing up mmap idx between evlist and evsel. That is going to matter whenevlist->all_cpus != evlist->user_requested_cpus != evsel->cpus:
libperf evsel: Factor out perf_evsel__ioctl() [now applied] libperf evsel: Add perf_evsel__enable_thread()
perf evlist: Use libperf functions in evlist__enable_event_idx() perf auxtrace: Move evlist__enable_event_idx() to auxtrace.c perf auxtrace: Do not mix up mmap idx
The next 6 patches stop attempts to auxtrace mmap when it is not an auxtrace event e.g. when mmapping the CPUs on which only sideband is captured:
libperf evlist: Remove ->idx() per_cpu parameter
libperf evlist: Move ->idx() into mmap_per_evsel()
libperf evlist: Add evsel as a parameter to ->idx()
perf auxtrace: Record whether an auxtrace mmap is needed perf auxctrace: Add mmap_needed to auxtrace_mmap_params perf auxtrace: Remove auxtrace_mmap_params__set_idx() per_cpu parameter
The next 5 patches switch to setting up dummy event maps before adding the evsel so that the evsel is subject to map propagation, primarily to cause addition of the evsel's CPUs to all_cpus.
perf evlist: Factor out evlist__dummy_event()
perf evlist: Add evlist__add_system_wide_dummy()
perf record: Use evlist__add_system_wide_dummy() in record__config_text_poke() perf intel-pt: Use evlist__add_system_wide_dummy() for switch tracking perf intel-pt: Track sideband system-wide when needed
The remaining patches make more significant changes.
First change from using user_requested_cpus to using all_cpus where necessary:
perf tools: Allow all_cpus to be a superset of user_requested_cpus
Secondly, mmap all per-thread and all per-cpu events:
libperf evlist: Allow mixing per-thread and per-cpu mmaps libperf evlist: Check nr_mmaps is correct [new in V1]
Stop using system_wide flag for uncore because it will not work anymore:
perf stat: Add requires_cpu flag for uncore libperf evsel: Add comments for booleans [new in V1]
Finally change map propagation so that system-wide events retain their cpus and (dummy) threads:
perf tools: Allow system-wide events to keep their own CPUs perf tools: Allow system-wide events to keep their own threads
Changes in V1:
perf intel-pt: Add a test for system-wide side band
New patch
libperf evsel: Factor out perf_evsel__ioctl()
Dropped because it has been applied.
libperf evsel: Add perf_evsel__enable_thread()
Rename variable i -> idx
perf auxtrace: Do not mix up mmap idx
Rename variable cpu to cpu_map_idx
perf tools: Allow all_cpus to be a superset of user_requested_cpus
Add Acked-by: Ian Rogers <[email protected]>
libperf evlist: Allow mixing per-thread and per-cpu mmaps
Fix perf_evlist__nr_mmaps() calculation
libperf evlist: Check nr_mmaps is correct
New patch
libperf evsel: Add comments for booleans
New patch
perf tools: Allow system-wide events to keep their own CPUs perf tools: Allow system-wide events to keep their own threads
Adrian Hunter (23):
perf intel-pt: Add a test for system-wide side band
libperf evsel: Add perf_evsel__enable_thread()
perf evlist: Use libperf functions in evlist__enable_event_idx() perf auxtrace: Move evlist__enable_event_idx() to auxtrace.c perf auxtrace: Do not mix up mmap idx
libperf evlist: Remove ->idx() per_cpu parameter
libperf evlist: Move ->idx() into mmap_per_evsel()
libperf evlist: Add evsel as a parameter to ->idx()
perf auxtrace: Record whether an auxtrace mmap is needed
perf auxtrace: Add mmap_needed to auxtrace_mmap_params
perf auxtrace: Remove auxtrace_mmap_params__set_idx() per_cpu parameter perf evlist: Factor out evlist__dummy_event()
perf evlist: Add evlist__add_system_wide_dummy()
perf record: Use evlist__add_system_wide_dummy() in record__config_text_poke() perf intel-pt: Use evlist__add_system_wide_dummy() for switch tracking perf intel-pt: Track sideband system-wide when needed
perf tools: Allow all_cpus to be a superset of user_requested_cpus libperf evlist: Allow mixing per-thread and per-cpu mmaps libperf evlist: Check nr_mmaps is correct
perf stat: Add requires_cpu flag for uncore
libperf evsel: Add comments for booleans
perf tools: Allow system-wide events to keep their own CPUs
perf tools: Allow system-wide events to keep their own threads
tools/lib/perf/evlist.c | 80 ++++++++++------------- tools/lib/perf/evsel.c | 10 +++ tools/lib/perf/include/internal/evlist.h | 3 +- tools/lib/perf/include/internal/evsel.h | 9 +++ tools/lib/perf/include/internal/mmap.h | 5 ++ tools/lib/perf/include/perf/evsel.h | 1 + tools/perf/arch/arm/util/cs-etm.c | 1 + tools/perf/arch/arm64/util/arm-spe.c | 1 + tools/perf/arch/s390/util/auxtrace.c | 1 + tools/perf/arch/x86/util/intel-bts.c | 1 + tools/perf/arch/x86/util/intel-pt.c | 32 ++++------ tools/perf/builtin-record.c | 39 +++++------- tools/perf/builtin-stat.c | 5 +- tools/perf/tests/shell/test_intel_pt.sh | 71 +++++++++++++++++++++ tools/perf/util/auxtrace.c | 31 +++++++-- tools/perf/util/auxtrace.h | 8 ++- tools/perf/util/evlist.c | 106 +++++++++++++++---------------- tools/perf/util/evlist.h | 7 +- tools/perf/util/evsel.c | 1 + tools/perf/util/evsel.h | 1 + tools/perf/util/mmap.c | 4 +- tools/perf/util/parse-events.c | 2 +- 22 files changed, 259 insertions(+), 160 deletions(-) create mode 100755 tools/perf/tests/shell/test_intel_pt.sh
Regards
Adrian
Adrian Hunter
reviewerPATCH 1/23 perf intel-pt: Add a test for system-wide side band
Add a test for system-wide side band even when tracing selected CPUs.
--- tools/perf/tests/shell/test_intel_pt.sh | 71 +++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100755 tools/perf/tests/shell/test_intel_pt.sh
tools/perf/tests/shell/test_intel_pt.sh new file +71 -0
@@ -0,0 +1,71 @@ +#!/bin/sh +# Miscellaneous Intel PT testing +# SPDX-License-Identifier: GPL-2.0 + +set -e + +# Skip if no Intel PT +perf list | grep -q 'intel_pt//' || exit 2 + +skip_cnt=0 +ok_cnt=0 +err_cnt=0 + +tmpfile=`mktemp` +perfdatafile=`mktemp` + +can_cpu_wide() +{ + perf record -o ${tmpfile} -B -N --no-bpf-event -e dummy:u -C $1 true 2>&1 >/dev/null || return 2 + return 0 +} + +test_system_wide_side_band() +{ + # Need CPU 0 and CPU 1 + can_cpu_wide 0 || return $? + can_cpu_wide 1 || return $? + + # Record on CPU 0 a task running on CPU 1 + perf record -B -N --no-bpf-event -o ${perfdatafile} -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname + + # Should get MMAP events from CPU 1 because they can be needed to decode + mmap_cnt=`perf script -i ${perfdatafile} --no-itrace --show-mmap-events -C 1 2>/dev/null | grep MMAP | wc -l` + + if [ ${mmap_cnt} -gt 0 ] ; then + return 0 + fi + + echo "Failed to record MMAP events on CPU 1 when tracing CPU 0" + return 1 +} + +count_result() +{ + if [ $1 -eq 2 ] ; then + skip_cnt=`expr ${skip_cnt} \+ 1` + return + fi + if [ $1 -eq 0 ] ; then + ok_cnt=`expr ${ok_cnt} \+ 1` + return + fi + err_cnt=`expr ${err_cnt} \+ 1` +} + +test_system_wide_side_band + +count_result $? + +rm -f ${tmpfile} +rm -f ${perfdatafile} + +if [ ${err_cnt} -gt 0 ] ; then + exit 1 +fi + +if [ ${ok_cnt} -gt 0 ] ; then + exit 0 +fi + +exit 2
Signature · 1 line
2.25.1
Re: [PATCH V1 01/23] perf intel-pt: Add a test for system-wide side band
Quoted 4 lines · Adrian Hunter
Add a test for system-wide side band even when tracing selected CPUs.
Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 85 lines
--- tools/perf/tests/shell/test_intel_pt.sh | 71 +++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100755 tools/perf/tests/shell/test_intel_pt.shtools/perf/tests/shell/test_intel_pt.sh new file +71
-1@@ -0,0 +1,71 @@ +#!/bin/sh +# Miscellaneous Intel PT testing +# SPDX-License-Identifier: GPL-2.0 + +set -e + +# Skip if no Intel PT +perf list | grep -q 'intel_pt//' || exit 2 + +skip_cnt=0 +ok_cnt=0 +err_cnt=0 + +tmpfile=`mktemp` +perfdatafile=`mktemp` + +can_cpu_wide() +{ + perf record -o ${tmpfile} -B -N --no-bpf-event -e dummy:u -C $1 true 2>&1 >/dev/null || return 2 + return 0 +} + +test_system_wide_side_band() +{ + # Need CPU 0 and CPU 1 + can_cpu_wide 0 || return $? + can_cpu_wide 1 || return $? + + # Record on CPU 0 a task running on CPU 1 + perf record -B -N --no-bpf-event -o ${perfdatafile} -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname + + # Should get MMAP events from CPU 1 because they can be needed to decode + mmap_cnt=`perf script -i ${perfdatafile} --no-itrace --show-mmap-events -C 1 2>/dev/null | grep MMAP | wc -l` + + if [ ${mmap_cnt} -gt 0 ] ; then + return 0 + fi + + echo "Failed to record MMAP events on CPU 1 when tracing CPU 0" + return 1 +} + +count_result() +{ + if [ $1 -eq 2 ] ; then + skip_cnt=`expr ${skip_cnt} \+ 1` + return + fi + if [ $1 -eq 0 ] ; then + ok_cnt=`expr ${ok_cnt} \+ 1` + return + fi + err_cnt=`expr ${err_cnt} \+ 1` +} + +test_system_wide_side_band + +count_result $? + +rm -f ${tmpfile} +rm -f ${perfdatafile} + +if [ ${err_cnt} -gt 0 ] ; then + exit 1 +fi + +if [ ${ok_cnt} -gt 0 ] ; then + exit 0 +fi + +exit 2 --2.25.1
Adrian Hunter
reviewerPATCH 2/23 libperf evsel: Add perf_evsel__enable_thread()
In reply to Adrian HunterAdd perf_evsel__enable_thread() as a counterpart to perf_evsel__enable_cpu(), to enable all events for a thread.
--- tools/lib/perf/evsel.c | 10 ++++++++++ tools/lib/perf/include/perf/evsel.h | 1 + 2 files changed, 11 insertions(+)
tools/lib/perf/evsel.c +10 -0
@@ -360,6 +360,16 @@ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , cpu_map_idx); } +int perf_evsel__enable_thread (struct perf_evsel *evsel,int thread) +{ +int err =0 ; +int idx; + +for (idx =0 ; idx <xyarray__max_x (evsel->fd) && !err; idx++) + err =perf_evsel__ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , idx, thread); +return err; +} +int perf_evsel__enable (struct perf_evsel *evsel) {int i;
tools/lib/perf/include/perf/evsel.h +1 -0
@@ -36,6 +36,7 @@ LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 02/23] libperf evsel: Add perf_evsel__enable_thread()
Quoted 15 lines · Adrian Hunter
Add
perf_evsel__enable_thread()as a counterpart toperf_evsel__enable_cpu(), to enable all events for a thread.Signed-off-by Adrian Hunter <[email protected]>--- tools/lib/perf/evsel.c | 10 ++++++++++ tools/lib/perf/include/perf/evsel.h | 1 + 2 files changed, 11 insertions(+)tools/lib/perf/evsel.c +0
-0
tools/lib/perf/evsel.c int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) · line 369
Quoted 10 lines
tools/lib/perf/evsel.c +7
-0@@ -360,6 +360,16 @@ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , cpu_map_idx); } +int perf_evsel__enable_thread (struct perf_evsel *evsel,int thread) +{ +int err =0 ; +int idx; + +for (idx =0 ; idx <xyarray__max_x (evsel->fd) && !err; idx++) + err =perf_evsel__ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , idx, thread);
For perf_cpu_map code like this has been replaced with perf_cpu_map__for_each_cpu, it would be nice here to use a perf_thread_map__for_each_thread. I understand we don't have that at the moment. It would be easier to find places to add this if there is a call to perf_thread_map__nr. Adding an assert of:
assert(perf_thread_map__nr(evsel->thread_map) == xyarray__max_x(evsel->fd));
Would help, or we could add the loop.
Thanks,
Ian
Quoted 21 lines
tools/lib/perf/evsel.c +3
-0+return err; +} +int perf_evsel__enable (struct perf_evsel *evsel) {int i;tools/lib/perf/include/perf/evsel.h +1
-1@@ -36,6 +36,7 @@ LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); --2.25.1
Adrian Hunter
reviewerRe: [PATCH V1 02/23] libperf evsel: Add perf_evsel__enable_thread()
Quoted 33 lines · Ian Rogers
Quoted 15 lines · Adrian Hunter
Add
perf_evsel__enable_thread()as a counterpart toperf_evsel__enable_cpu(), to enable all events for a thread.Signed-off-by Adrian Hunter <[email protected]>--- tools/lib/perf/evsel.c | 10 ++++++++++ tools/lib/perf/include/perf/evsel.h | 1 + 2 files changed, 11 insertions(+)tools/lib/perf/evsel.c +0
-0tools/lib/perf/evsel.c int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) · line 369
Quoted 10 lines
tools/lib/perf/evsel.c +7
-0@@ -360,6 +360,16 @@ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , cpu_map_idx); } +int perf_evsel__enable_thread (struct perf_evsel *evsel,int thread) +{ +int err =0 ; +int idx; + +for (idx =0 ; idx <xyarray__max_x (evsel->fd) && !err; idx++) + err =perf_evsel__ioctl (evsel,PERF_EVENT_IOC_ENABLE ,NULL , idx, thread);For
perf_cpu_mapcode like this has been replaced withperf_cpu_map__for_each_cpu, it would be nice here to use aperf_thread_map__for_each_thread. I understand we don't have that at the moment. It would be easier to find places to add this if there is a call toperf_thread_map__nr. Adding an assert of:
Quoted 1 line
assert(perf_thread_map__nr(evsel->thread_map) == xyarray__max_x(evsel->fd));
Threads go in the y direction.
I'll change it to use perf_cpu_map__for_each_cpu
Quoted 27 lines
Would help, or we could add the loop.
Thanks,
IanQuoted 21 lines
tools/lib/perf/evsel.c +3
-0+return err; +} +int perf_evsel__enable (struct perf_evsel *evsel) {int i;tools/lib/perf/include/perf/evsel.h +1
-1@@ -36,6 +36,7 @@ LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); --2.25.1
Adrian Hunter
reviewerPATCH 3/23 perf evlist: Use libperf functions in evlist__enable_event_idx()
In reply to Adrian Hunterevlist__enable_event_idx() is used only for auxtrace events which are never system_wide. Simplify by using libperf enable event functions.
--- tools/perf/util/evlist.c | 44 ++-------------------------------------- 1 file changed, 2 insertions(+), 42 deletions(-)
tools/perf/util/evlist.c +2 -42
@@ -334,14 +334,6 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,return 0 ; } -static int evlist__nr_threads (struct evlist *evlist,struct evsel *evsel) -{ -if (evsel->core.system_wide) -return 1 ; -else -return perf_thread_map__nr (evlist->core.threads); -} -struct evlist_cpu_iterator evlist__cpu_begin (struct evlist *evlist,struct affinity *affinity) {struct evlist_cpu_iterator itr = {
@@ -546,46 +538,14 @@ void evlist__toggle_enable(struct evlist *evlist) (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int evlist__enable_event_cpu (struct evlist *evlist,struct evsel *evsel,int cpu) -{ -int thread; -int nr_threads =evlist__nr_threads (evlist, evsel); - -if (!evsel->core.fd) -return -EINVAL ; - -for (thread =0 ; thread < nr_threads; thread++) { -int err =ioctl (FD (evsel, cpu, thread),PERF_EVENT_IOC_ENABLE ,0 ); -if (err) -return err; - } -return 0 ; -} - -static int evlist__enable_event_thread (struct evlist *evlist,struct evsel *evsel,int thread) -{ -int cpu; -int nr_cpus =perf_cpu_map__nr (evlist->core.user_requested_cpus); - -if (!evsel->core.fd) -return -EINVAL ; - -for (cpu =0 ; cpu < nr_cpus; cpu++) { -int err =ioctl (FD (evsel, cpu, thread),PERF_EVENT_IOC_ENABLE ,0 ); -if (err) -return err; - } -return 0 ; -} -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) {bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus);if (per_cpu_mmaps) -return evlist__enable_event_cpu (evlist, evsel, idx); +return perf_evsel__enable_cpu (&evsel->core, idx); -return evlist__enable_event_thread (evlist, evsel, idx); +return perf_evsel__enable_thread (&evsel->core, idx); }int evlist__add_pollfd (struct evlist *evlist,int fd)
Signature · 1 line
2.25.1
Re: [PATCH V1 03/23] perf evlist: Use libperf functions in evlist__enable_event_idx()
Quoted 5 lines · Adrian Hunter
evlist__enable_event_idx()is used only for auxtrace events which are neversystem_wide. Simplify by using libperf enable event functions.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 75 lines
--- tools/perf/util/evlist.c | 44 ++-------------------------------------- 1 file changed, 2 insertions(+), 42 deletions(-)tools/perf/util/evlist.c +2
-43@@ -334,14 +334,6 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,return 0 ; } -static int evlist__nr_threads (struct evlist *evlist,struct evsel *evsel) -{ -if (evsel->core.system_wide) -return 1 ; -else -return perf_thread_map__nr (evlist->core.threads); -} -struct evlist_cpu_iterator evlist__cpu_begin (struct evlist *evlist,struct affinity *affinity) {struct evlist_cpu_iterator itr = {@@ -546,46 +538,14 @@ void evlist__toggle_enable(struct evlist *evlist) (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int evlist__enable_event_cpu (struct evlist *evlist,struct evsel *evsel,int cpu) -{ -int thread; -int nr_threads =evlist__nr_threads (evlist, evsel); - -if (!evsel->core.fd) -return -EINVAL ; - -for (thread =0 ; thread < nr_threads; thread++) { -int err =ioctl (FD (evsel, cpu, thread),PERF_EVENT_IOC_ENABLE ,0 ); -if (err) -return err; - } -return 0 ; -} - -static int evlist__enable_event_thread (struct evlist *evlist,struct evsel *evsel,int thread) -{ -int cpu; -int nr_cpus =perf_cpu_map__nr (evlist->core.user_requested_cpus); - -if (!evsel->core.fd) -return -EINVAL ; - -for (cpu =0 ; cpu < nr_cpus; cpu++) { -int err =ioctl (FD (evsel, cpu, thread),PERF_EVENT_IOC_ENABLE ,0 ); -if (err) -return err; - } -return 0 ; -} -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) {bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus);if (per_cpu_mmaps) -return evlist__enable_event_cpu (evlist, evsel, idx); +return perf_evsel__enable_cpu (&evsel->core, idx); -return evlist__enable_event_thread (evlist, evsel, idx); +return perf_evsel__enable_thread (&evsel->core, idx); }int evlist__add_pollfd (struct evlist *evlist,int fd) --2.25.1
Adrian Hunter
reviewerPATCH 4/23 perf auxtrace: Move evlist__enable_event_idx() to auxtrace.c
In reply to Adrian Hunterevlist__enable_event_idx() is used only by auxtrace. Move it to auxtrace.c in preparation for making it even more auxtrace specific.
--- tools/perf/util/auxtrace.c | 10 ++++++++++ tools/perf/util/evlist.c | 10 ---------- tools/perf/util/evlist.h | 2 -- 3 files changed, 10 insertions(+), 12 deletions(-)
tools/perf/util/auxtrace.c +10 -0
@@ -636,6 +636,16 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,return -EINVAL ; } +static int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) +{ +bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); + +if (per_cpu_mmaps) +return perf_evsel__enable_cpu (&evsel->core, idx); + +return perf_evsel__enable_thread (&evsel->core, idx); +} +int auxtrace_record__read_finish (struct auxtrace_record *itr,int idx) {struct evsel *evsel;
tools/perf/util/evlist.c +0 -10
@@ -538,16 +538,6 @@ void evlist__toggle_enable(struct evlist *evlist) (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) -{ -bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); - -if (per_cpu_mmaps) -return perf_evsel__enable_cpu (&evsel->core, idx); - -return perf_evsel__enable_thread (&evsel->core, idx); -} -int evlist__add_pollfd (struct evlist *evlist,int fd) {return perf_evlist__add_pollfd (&evlist->core, fd,NULL ,POLLIN , fdarray_flag__default);
tools/perf/util/evlist.h +0 -2
@@ -196,8 +196,6 @@ void evlist__toggle_enable(struct evlist *evlist);void evlist__disable_evsel (struct evlist *evlist,char *evsel_name);void evlist__enable_evsel (struct evlist *evlist,char *evsel_name); -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx); -void evlist__set_selected (struct evlist *evlist,struct evsel *evsel);int evlist__create_maps (struct evlist *evlist,struct target *target);
Signature · 1 line
2.25.1
Re: [PATCH V1 04/23] perf auxtrace: Move evlist__enable_event_idx() to auxtrace.c
Quoted 5 lines · Adrian Hunter
evlist__enable_event_idx()is used only by auxtrace. Move it toauxtrace.cin preparation for making it even more auxtrace specific.Signed-off-by Adrian Hunter <[email protected]>
Whilst this offends my object oriented encapsulation sensibilities, it is in the style of the current code and not recommended against by any style guide.
Thanks,
Ian
Quoted 64 lines
--- tools/perf/util/auxtrace.c | 10 ++++++++++ tools/perf/util/evlist.c | 10 ---------- tools/perf/util/evlist.h | 2 -- 3 files changed, 10 insertions(+), 12 deletions(-)tools/perf/util/auxtrace.c +10
-0@@ -636,6 +636,16 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,return -EINVAL ; } +static int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) +{ +bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); + +if (per_cpu_mmaps) +return perf_evsel__enable_cpu (&evsel->core, idx); + +return perf_evsel__enable_thread (&evsel->core, idx); +} +int auxtrace_record__read_finish (struct auxtrace_record *itr,int idx) {struct evsel *evsel;tools/perf/util/evlist.c +0
-10@@ -538,16 +538,6 @@ void evlist__toggle_enable(struct evlist *evlist) (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx) -{ -bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); - -if (per_cpu_mmaps) -return perf_evsel__enable_cpu (&evsel->core, idx); - -return perf_evsel__enable_thread (&evsel->core, idx); -} -int evlist__add_pollfd (struct evlist *evlist,int fd) {return perf_evlist__add_pollfd (&evlist->core, fd,NULL ,POLLIN , fdarray_flag__default);tools/perf/util/evlist.h +0
-3@@ -196,8 +196,6 @@ void evlist__toggle_enable(struct evlist *evlist);void evlist__disable_evsel (struct evlist *evlist,char *evsel_name);void evlist__enable_evsel (struct evlist *evlist,char *evsel_name); -int evlist__enable_event_idx (struct evlist *evlist,struct evsel *evsel,int idx); -void evlist__set_selected (struct evlist *evlist,struct evsel *evsel);int evlist__create_maps (struct evlist *evlist,struct target *target); --2.25.1
Adrian Hunter
reviewerPATCH 5/23 perf auxtrace: Do not mix up mmap idx
In reply to Adrian HunterThe idx is with respect to evlist not evsel. That hasn't mattered because they are the same at present. Prepare for that not being the case, which it won't be when sideband tracking events are allowed on all CPUs even when auxtrace is limited to selected CPUs.
--- tools/perf/util/auxtrace.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
tools/perf/util/auxtrace.c +8 -2
@@ -640,8 +640,14 @@ static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, {bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); -if (per_cpu_mmaps) -return perf_evsel__enable_cpu (&evsel->core, idx); +if (per_cpu_mmaps) { +struct perf_cpu evlist_cpu =perf_cpu_map__cpu (evlist->core.all_cpus, idx); +int cpu_map_idx =perf_cpu_map__idx (evsel->core.cpus, evlist_cpu); + +if (cpu_map_idx ==-1 ) +return -EINVAL ; +return perf_evsel__enable_cpu (&evsel->core, cpu_map_idx); + }return perf_evsel__enable_thread (&evsel->core, idx); }
Signature · 1 line
2.25.1
Re: [PATCH V1 05/23] perf auxtrace: Do not mix up mmap idx
Quoted 7 lines · Adrian Hunter
The idx is with respect to evlist not evsel. That hasn't mattered because they are the same at present. Prepare for that not being the case, which it won't be when sideband tracking events are allowed on all CPUs even when auxtrace is limited to selected CPUs.
Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 28 lines
--- tools/perf/util/auxtrace.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)tools/perf/util/auxtrace.c +8
-3@@ -640,8 +640,14 @@ static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, {bool per_cpu_mmaps = !perf_cpu_map__empty (evlist->core.user_requested_cpus); -if (per_cpu_mmaps) -return perf_evsel__enable_cpu (&evsel->core, idx); +if (per_cpu_mmaps) { +struct perf_cpu evlist_cpu =perf_cpu_map__cpu (evlist->core.all_cpus, idx); +int cpu_map_idx =perf_cpu_map__idx (evsel->core.cpus, evlist_cpu); + +if (cpu_map_idx ==-1 ) +return -EINVAL ; +return perf_evsel__enable_cpu (&evsel->core, cpu_map_idx); + }return perf_evsel__enable_thread (&evsel->core, idx); } --2.25.1
Adrian Hunter
reviewerPATCH 6/23 libperf evlist: Remove ->idx() per_cpu parameter
In reply to Adrian HunterRemove ->idx() per_cpu parameter because it isn't needed.
--- tools/lib/perf/evlist.c | 4 ++-- tools/lib/perf/include/internal/evlist.h | 2 +- tools/perf/util/evlist.c | 3 ++- 3 files changed, 5 insertions(+), 4 deletions(-)
tools/lib/perf/evlist.c +2 -2
@@ -517,7 +517,7 @@ mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output_overwrite =-1 ;if (ops->idx) - ops->idx (evlist, mp, thread, false); + ops->idx (evlist, mp, thread);if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, &output, &output_overwrite))
@@ -544,7 +544,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output_overwrite =-1 ;if (ops->idx) - ops->idx (evlist, mp, cpu, true); + ops->idx (evlist, mp, cpu);for (thread =0 ; thread < nr_threads; thread++) { if (mmap_per_evsel(evlist, ops, cpu, mp, cpu,
tools/lib/perf/include/internal/evlist.h +1 -1
@@ -38,7 +38,7 @@ struct perf_evlist { };typedef void -(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int ,bool ); +(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int );typedef struct perf_mmap * (*perf_evlist_mmap__cb_get_t )(struct perf_evlist *,bool ,int ); typedef int
tools/perf/util/evlist.c +2 -1
@@ -748,10 +748,11 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist,struct perf_mmap_param *_mp, -int idx,bool per_cpu) +int idx) { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); +bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus);auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, idx, per_cpu); }
Signature · 1 line
2.25.1
Re: [PATCH V1 06/23] libperf evlist: Remove ->idx() per_cpu parameter
Quoted 4 lines · Adrian Hunter
Remove ->idx()
per_cpuparameter because it isn't needed.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 61 lines
--- tools/lib/perf/evlist.c | 4 ++-- tools/lib/perf/include/internal/evlist.h | 2 +- tools/perf/util/evlist.c | 3 ++- 3 files changed, 5 insertions(+), 4 deletions(-)tools/lib/perf/evlist.c +2
-2@@ -517,7 +517,7 @@ mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output_overwrite =-1 ;if (ops->idx) - ops->idx (evlist, mp, thread, false); + ops->idx (evlist, mp, thread);if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, &output, &output_overwrite))@@ -544,7 +544,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output_overwrite =-1 ;if (ops->idx) - ops->idx (evlist, mp, cpu, true); + ops->idx (evlist, mp, cpu);for (thread =0 ; thread < nr_threads; thread++) { if (mmap_per_evsel(evlist, ops, cpu, mp, cpu,tools/lib/perf/include/internal/evlist.h +1
-1@@ -38,7 +38,7 @@ struct perf_evlist { };typedef void -(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int ,bool ); +(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int );typedef struct perf_mmap * (*perf_evlist_mmap__cb_get_t )(struct perf_evlist *,bool ,int ); typedef inttools/perf/util/evlist.c +2
-2@@ -748,10 +748,11 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist,struct perf_mmap_param *_mp, -int idx,bool per_cpu) +int idx) { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); +bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus);auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, idx, per_cpu); } --2.25.1
Adrian Hunter
reviewerPATCH 7/23 libperf evlist: Move ->idx() into mmap_per_evsel()
In reply to Adrian HunterMove ->idx() into mmap_per_evsel() in preparation for adding evsel as a parameter.
--- tools/lib/perf/evlist.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
tools/lib/perf/evlist.c +3 -6
@@ -474,6 +474,9 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,*/ refcount_set (&map->refcnt,2 ); +if (ops->idx) + ops->idx (evlist, mp, idx); +if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ;
@@ -516,9 +519,6 @@ mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output =-1 ;int output_overwrite =-1 ; -if (ops->idx) - ops->idx (evlist, mp, thread); -if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, &output, &output_overwrite)) goto out_unmap;
@@ -543,9 +543,6 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output =-1 ;int output_overwrite =-1 ; -if (ops->idx) - ops->idx (evlist, mp, cpu); -for (thread =0 ; thread < nr_threads; thread++) {if (mmap_per_evsel (evlist, ops, cpu, mp, cpu, thread, &output, &output_overwrite))
Signature · 1 line
2.25.1
Re: [PATCH V1 07/23] libperf evlist: Move ->idx() into mmap_per_evsel()
Quoted 5 lines · Adrian Hunter
Move ->idx() into
mmap_per_evsel()in preparation for adding evsel as a parameter.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 41 lines
--- tools/lib/perf/evlist.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)tools/lib/perf/evlist.c +3
-7@@ -474,6 +474,9 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,*/ refcount_set (&map->refcnt,2 ); +if (ops->idx) + ops->idx (evlist, mp, idx); +if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ;@@ -516,9 +519,6 @@ mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output =-1 ;int output_overwrite =-1 ; -if (ops->idx) - ops->idx (evlist, mp, thread); -if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, &output, &output_overwrite)) goto out_unmap;@@ -543,9 +543,6 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,int output =-1 ;int output_overwrite =-1 ; -if (ops->idx) - ops->idx (evlist, mp, cpu); -for (thread =0 ; thread < nr_threads; thread++) {if (mmap_per_evsel (evlist, ops, cpu, mp, cpu, thread, &output, &output_overwrite)) --2.25.1
Adrian Hunter
reviewerPATCH 8/23 libperf evlist: Add evsel as a parameter to ->idx()
In reply to Adrian HunterAdd evsel as a parameter to ->idx() in preparation for correctly determining whether an auxtrace mmap is needed.
--- tools/lib/perf/evlist.c | 2 +- tools/lib/perf/include/internal/evlist.h | 3 ++- tools/perf/util/evlist.c | 1 + 3 files changed, 4 insertions(+), 2 deletions(-)
tools/lib/perf/evlist.c +1 -1
@@ -475,7 +475,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,refcount_set (&map->refcnt,2 );if (ops->idx) - ops->idx (evlist, mp, idx); + ops->idx (evlist, evsel, mp, idx);if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ;
tools/lib/perf/include/internal/evlist.h +2 -1
@@ -38,7 +38,8 @@ struct perf_evlist { };typedef void -(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int ); +(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_evsel *, +struct perf_mmap_param *,int );typedef struct perf_mmap * (*perf_evlist_mmap__cb_get_t )(struct perf_evlist *,bool ,int ); typedef int
tools/perf/util/evlist.c +1 -0
@@ -747,6 +747,7 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist, +struct perf_evsel *_evsel__maybe_unused ,struct perf_mmap_param *_mp,int idx) {
Signature · 1 line
2.25.1
Re: [PATCH V1 08/23] libperf evlist: Add evsel as a parameter to ->idx()
Quoted 5 lines · Adrian Hunter
Add evsel as a parameter to ->idx() in preparation for correctly determining whether an auxtrace mmap is needed.
Signed-off-by Adrian Hunter <[email protected]>
Just to note that in the non-lib version of evsel there is a back link to the evlist. If we ever had that in the lib version then there'd be no need to pass the evsel and evlist.
Thanks,
Ian
Quoted 48 lines
--- tools/lib/perf/evlist.c | 2 +- tools/lib/perf/include/internal/evlist.h | 3 ++- tools/perf/util/evlist.c | 1 + 3 files changed, 4 insertions(+), 2 deletions(-)tools/lib/perf/evlist.c +1
-1@@ -475,7 +475,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,refcount_set (&map->refcnt,2 );if (ops->idx) - ops->idx (evlist, mp, idx); + ops->idx (evlist, evsel, mp, idx);if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ;tools/lib/perf/include/internal/evlist.h +2
-1@@ -38,7 +38,8 @@ struct perf_evlist { };typedef void -(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_mmap_param *,int ); +(*perf_evlist_mmap__cb_idx_t )(struct perf_evlist *,struct perf_evsel *, +struct perf_mmap_param *,int );typedef struct perf_mmap * (*perf_evlist_mmap__cb_get_t )(struct perf_evlist *,bool ,int ); typedef inttools/perf/util/evlist.c +1
-1@@ -747,6 +747,7 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist, +struct perf_evsel *_evsel__maybe_unused ,struct perf_mmap_param *_mp,int idx) { --2.25.1
Adrian Hunter
reviewerPATCH 9/23 perf auxtrace: Record whether an auxtrace mmap is needed
In reply to Adrian HunterAdd a flag needs_auxtrace_mmap to record whether an auxtrace mmap is needed, in preparation for correctly determining whether or not an auxtrace mmap is needed.
--- tools/perf/arch/arm/util/cs-etm.c | 1 + tools/perf/arch/arm64/util/arm-spe.c | 1 + tools/perf/arch/s390/util/auxtrace.c | 1 + tools/perf/arch/x86/util/intel-bts.c | 1 + tools/perf/arch/x86/util/intel-pt.c | 1 + tools/perf/util/evsel.h | 1 + 6 files changed, 6 insertions(+)
tools/perf/arch/arm/util/cs-etm.c +1 -0
@@ -319,6 +319,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; + evsel->needs_auxtrace_mmap = true; cs_etm_evsel = evsel; opts->full_auxtrace = true; }
tools/perf/arch/arm64/util/arm-spe.c +1 -0
@@ -160,6 +160,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period; + evsel->needs_auxtrace_mmap = true; arm_spe_evsel = evsel; opts->full_auxtrace = true; }
tools/perf/arch/s390/util/auxtrace.c +1 -0
@@ -98,6 +98,7 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,evlist__for_each_entry (evlist, pos) {if (pos->core.attr.config ==PERF_EVENT_CPUM_SF_DIAG ) { diagnose =1 ; + pos->needs_auxtrace_mmap = true;break ; } }
tools/perf/arch/x86/util/intel-bts.c +1 -0
@@ -129,6 +129,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; + evsel->needs_auxtrace_mmap = true; intel_bts_evsel = evsel; opts->full_auxtrace = true; }
tools/perf/arch/x86/util/intel-pt.c +1 -0
@@ -649,6 +649,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; evsel->no_aux_samples = true; + evsel->needs_auxtrace_mmap = true; intel_pt_evsel = evsel; opts->full_auxtrace = true; }
tools/perf/util/evsel.h +1 -0
@@ -124,6 +124,7 @@ struct evsel {bool merged_stat;bool reset_group;bool errored; +bool needs_auxtrace_mmap;struct hashmap *per_pkg_mask;int err;struct {
Signature · 1 line
2.25.1
Re: [PATCH V1 09/23] perf auxtrace: Record whether an auxtrace mmap is needed
Quoted 6 lines · Adrian Hunter
Add a flag
needs_auxtrace_mmapto record whether an auxtrace mmap is needed, in preparation for correctly determining whether or not an auxtrace mmap is needed.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 84 lines
--- tools/perf/arch/arm/util/cs-etm.c | 1 + tools/perf/arch/arm64/util/arm-spe.c | 1 + tools/perf/arch/s390/util/auxtrace.c | 1 + tools/perf/arch/x86/util/intel-bts.c | 1 + tools/perf/arch/x86/util/intel-pt.c | 1 + tools/perf/util/evsel.h | 1 + 6 files changed, 6 insertions(+)tools/perf/arch/arm/util/cs-etm.c +1
-0@@ -319,6 +319,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; + evsel->needs_auxtrace_mmap = true; cs_etm_evsel = evsel; opts->full_auxtrace = true; }tools/perf/arch/arm64/util/arm-spe.c +1
-0@@ -160,6 +160,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period; + evsel->needs_auxtrace_mmap = true; arm_spe_evsel = evsel; opts->full_auxtrace = true; }tools/perf/arch/s390/util/auxtrace.c +1
-0@@ -98,6 +98,7 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,evlist__for_each_entry (evlist, pos) {if (pos->core.attr.config ==PERF_EVENT_CPUM_SF_DIAG ) { diagnose =1 ; + pos->needs_auxtrace_mmap = true;break ; } }tools/perf/arch/x86/util/intel-bts.c +1
-0@@ -129,6 +129,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; + evsel->needs_auxtrace_mmap = true; intel_bts_evsel = evsel; opts->full_auxtrace = true; }tools/perf/arch/x86/util/intel-pt.c +1
-0@@ -649,6 +649,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, evsel->core.attr.freq =0 ; evsel->core.attr.sample_period =1 ; evsel->no_aux_samples = true; + evsel->needs_auxtrace_mmap = true; intel_pt_evsel = evsel; opts->full_auxtrace = true; }tools/perf/util/evsel.h +1
-1@@ -124,6 +124,7 @@ struct evsel {bool merged_stat;bool reset_group;bool errored; +bool needs_auxtrace_mmap;struct hashmap *per_pkg_mask;int err;struct { --2.25.1
Adrian Hunter
reviewerPATCH 10/23 perf auxtrace: Add mmap_needed to auxtrace_mmap_params
In reply to Adrian HunterAdd mmap_needed to auxtrace_mmap_params.
Currently an auxtrace mmap is always attempted even if the event is not an auxtrace event. That works because, when AUX area tracing, there is always an auxtrace event first for every mmap. Prepare for that not being the case, which it won't be when sideband tracking events are allowed on all CPUs even when auxtrace is limited to selected CPUs.
--- tools/perf/util/auxtrace.c | 10 ++++++++-- tools/perf/util/auxtrace.h | 7 +++++-- tools/perf/util/evlist.c | 5 +++-- tools/perf/util/mmap.c | 1 + 4 files changed, 17 insertions(+), 6 deletions(-)
tools/perf/util/auxtrace.c +8 -2
@@ -125,7 +125,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, mm->tid = mp->tid; mm->cpu = mp->cpu.cpu; -if (!mp->len) { +if (!mp->len || !mp->mmap_needed) { mm->base =NULL ;return 0 ; }
@@ -168,9 +168,15 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, }void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu) { + mp->mmap_needed = evsel->needs_auxtrace_mmap; + +if (!mp->mmap_needed) +return ; + mp->idx = idx;if (per_cpu) {
tools/perf/util/auxtrace.h +5 -2
@@ -353,6 +353,7 @@ struct auxtrace_mmap_params {int prot;int idx;pid_t tid; +bool mmap_needed;struct perf_cpu cpu; };
@@ -490,7 +491,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,unsigned int auxtrace_pages, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool,
@@ -863,7 +865,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,unsigned int auxtrace_pages, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu);#define ITRACE_HELP ""
tools/perf/util/evlist.c +3 -2
@@ -747,15 +747,16 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist, -struct perf_evsel *_evsel__maybe_unused , +struct perf_evsel *_evsel,struct perf_mmap_param *_mp,int idx) { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core);bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus); + struct evsel *evsel = container_of(_evsel, struct evsel, core); -auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, idx, per_cpu); +auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx, per_cpu); } static struct perf_mmap*
tools/perf/util/mmap.c +1 -0
@@ -62,6 +62,7 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_uvoid __weak auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp__maybe_unused ,struct evlist *evlist__maybe_unused , +struct evsel *evsel__maybe_unused ,int idx__maybe_unused ,bool per_cpu__maybe_unused ) {
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 10/23] perf auxtrace: Add mmap_needed to auxtrace_mmap_params
Quoted 52 lines · Adrian Hunter
Add
mmap_neededtoauxtrace_mmap_params.Currently an auxtrace mmap is always attempted even if the event is not an auxtrace event. That works because, when AUX area tracing, there is always an auxtrace event first for every mmap. Prepare for that not being the case, which it won't be when sideband tracking events are allowed on all CPUs even when auxtrace is limited to selected CPUs.
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/auxtrace.c | 10 ++++++++-- tools/perf/util/auxtrace.h | 7 +++++-- tools/perf/util/evlist.c | 5 +++-- tools/perf/util/mmap.c | 1 + 4 files changed, 17 insertions(+), 6 deletions(-)tools/perf/util/auxtrace.c +8
-2@@ -125,7 +125,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, mm->tid = mp->tid; mm->cpu = mp->cpu.cpu; -if (!mp->len) { +if (!mp->len || !mp->mmap_needed) { mm->base =NULL ;return 0 ; }@@ -168,9 +168,15 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, }void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu) { + mp->mmap_needed = evsel->needs_auxtrace_mmap; + +if (!mp->mmap_needed) +return ; + mp->idx = idx;if (per_cpu) {tools/perf/util/auxtrace.h +0
-0
tools/perf/util/auxtrace.h struct auxtrace_mmap_params { · line 356
Quoted 4 lines
tools/perf/util/auxtrace.h +1
-0@@ -353,6 +353,7 @@ struct auxtrace_mmap_params {int prot;int idx;pid_t tid; +bool mmap_needed;
It'd be useful to add or fix some context documentation here. Above it says:
* struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
but this flag seems intended for the operation to fail. Clarifying the intention of the flag would be useful.
Thanks,
Ian
Quoted 61 lines
tools/perf/util/auxtrace.h +4
-2struct perf_cpu cpu; };@@ -490,7 +491,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,unsigned int auxtrace_pages, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool,@@ -863,7 +865,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,unsigned int auxtrace_pages, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp, -struct evlist *evlist,int idx, +struct evlist *evlist, +struct evsel *evsel,int idx,bool per_cpu);#define ITRACE_HELP ""tools/perf/util/evlist.c +3
-2@@ -747,15 +747,16 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,static void perf_evlist__mmap_cb_idx (struct perf_evlist *_evlist, -struct perf_evsel *_evsel__maybe_unused , +struct perf_evsel *_evsel,struct perf_mmap_param *_mp,int idx) { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core);bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus); + struct evsel *evsel = container_of(_evsel, struct evsel, core); -auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, idx, per_cpu); +auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx, per_cpu); } static struct perf_mmap*tools/perf/util/mmap.c +1
-1@@ -62,6 +62,7 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_uvoid __weak auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp__maybe_unused ,struct evlist *evlist__maybe_unused , +struct evsel *evsel__maybe_unused ,int idx__maybe_unused ,bool per_cpu__maybe_unused ) { --2.25.1
Adrian Hunter
reviewerPATCH 11/23 perf auxtrace: Remove auxtrace_mmap_params__set_idx() per_cpu parameter
In reply to Adrian HunterRemove auxtrace_mmap_params__set_idx() per_cpu parameter because it isn't needed.
--- tools/perf/util/auxtrace.c | 5 +++-- tools/perf/util/auxtrace.h | 3 +-- tools/perf/util/evlist.c | 3 +-- tools/perf/util/mmap.c | 3 +-- 4 files changed, 6 insertions(+), 8 deletions(-)
tools/perf/util/auxtrace.c +3 -2
@@ -169,9 +169,10 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp,struct evlist *evlist, -struct evsel *evsel,int idx, -bool per_cpu) +struct evsel *evsel,int idx) { +bool per_cpu = !perf_cpu_map__empty (evlist->core.user_requested_cpus); + mp->mmap_needed = evsel->needs_auxtrace_mmap;if (!mp->mmap_needed)
tools/perf/util/auxtrace.h +1 -2
@@ -492,8 +492,7 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp,struct evlist *evlist, -struct evsel *evsel,int idx, -bool per_cpu); +struct evsel *evsel,int idx); typedef int (*process_auxtrace_t)(struct perf_tool *tool, struct mmap *map,
tools/perf/util/evlist.c +1 -2
@@ -753,10 +753,9 @@ perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist, { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); -bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus); struct evsel *evsel = container_of(_evsel, struct evsel, core); -auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx, per_cpu); +auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx); } static struct perf_mmap*
tools/perf/util/mmap.c +1 -2
@@ -63,8 +63,7 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_uvoid __weak auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp__maybe_unused ,struct evlist *evlist__maybe_unused ,struct evsel *evsel__maybe_unused , -int idx__maybe_unused , -bool per_cpu__maybe_unused ) +int idx__maybe_unused ) { }
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 11/23] perf auxtrace: Remove auxtrace_mmap_params__set_idx() per_cpu parameter
Quoted 34 lines · Adrian Hunter
Remove
auxtrace_mmap_params__set_idx()per_cpuparameter because it isn't needed.Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/auxtrace.c | 5 +++-- tools/perf/util/auxtrace.h | 3 +-- tools/perf/util/evlist.c | 3 +-- tools/perf/util/mmap.c | 3 +-- 4 files changed, 6 insertions(+), 8 deletions(-)tools/perf/util/auxtrace.c +3
-2@@ -169,9 +169,10 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp,struct evlist *evlist, -struct evsel *evsel,int idx, -bool per_cpu) +struct evsel *evsel,int idx) { +bool per_cpu = !perf_cpu_map__empty (evlist->core.user_requested_cpus); + mp->mmap_needed = evsel->needs_auxtrace_mmap;if (!mp->mmap_needed)tools/perf/util/auxtrace.h +0
-0
tools/perf/util/auxtrace.h void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, · line 495
Quoted 6 lines
tools/perf/util/auxtrace.h +1
-2@@ -492,8 +492,7 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, bool auxtrace_overwrite);void auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp,struct evlist *evlist, -struct evsel *evsel,int idx, -bool per_cpu); +struct evsel *evsel,int idx);
A similar change is needed on line 868 for when HAVE_AUXTRACE_SUPPORT isn't defined.
Thanks,
Ian
Quoted 36 lines
tools/perf/util/auxtrace.h +0
-0typedef int (*process_auxtrace_t)(struct perf_tool *tool, struct mmap *map,tools/perf/util/evlist.c +1
-2@@ -753,10 +753,9 @@ perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist, { struct evlist *evlist = container_of(_evlist, struct evlist, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); -bool per_cpu = !perf_cpu_map__empty (_evlist->user_requested_cpus); struct evsel *evsel = container_of(_evsel, struct evsel, core); -auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx, per_cpu); +auxtrace_mmap_params__set_idx (&mp->auxtrace_mp, evlist, evsel, idx); } static struct perf_mmap*tools/perf/util/mmap.c +1
-3@@ -63,8 +63,7 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_uvoid __weak auxtrace_mmap_params__set_idx (struct auxtrace_mmap_params *mp__maybe_unused ,struct evlist *evlist__maybe_unused ,struct evsel *evsel__maybe_unused , -int idx__maybe_unused , -bool per_cpu__maybe_unused ) +int idx__maybe_unused ) { } --2.25.1
Adrian Hunter
reviewerPATCH 12/23 perf evlist: Factor out evlist__dummy_event()
In reply to Adrian HunterFactor out evlist__dummy_event() so it can be reused.
--- tools/perf/util/evlist.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
tools/perf/util/evlist.c +8 -2
@@ -242,14 +242,20 @@ int __evlist__add_default(struct evlist *evlist, bool precise)return 0 ; } -int evlist__add_dummy (struct evlist *evlist) +static struct evsel *evlist__dummy_event (struct evlist *evlist) {struct perf_event_attr attr = { .type =PERF_TYPE_SOFTWARE , .config =PERF_COUNT_SW_DUMMY , .size =sizeof (attr),/* to capture ABI version */ }; -struct evsel *evsel =evsel__new_idx (&attr, evlist->core.nr_entries); + +return evsel__new_idx (&attr, evlist->core.nr_entries); +} + +int evlist__add_dummy (struct evlist *evlist) +{ +struct evsel *evsel =evlist__dummy_event (evlist);if (evsel ==NULL )return -ENOMEM ;
Signature · 1 line
2.25.1
Re: [PATCH V1 12/23] perf evlist: Factor out evlist__dummy_event()
Quoted 4 lines · Adrian Hunter
Factor out
evlist__dummy_event()so it can be reused.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 34 lines
--- tools/perf/util/evlist.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)tools/perf/util/evlist.c +8
-3@@ -242,14 +242,20 @@ int __evlist__add_default(struct evlist *evlist, bool precise)return 0 ; } -int evlist__add_dummy (struct evlist *evlist) +static struct evsel *evlist__dummy_event (struct evlist *evlist) {struct perf_event_attr attr = { .type =PERF_TYPE_SOFTWARE , .config =PERF_COUNT_SW_DUMMY , .size =sizeof (attr),/* to capture ABI version */ }; -struct evsel *evsel =evsel__new_idx (&attr, evlist->core.nr_entries); + +return evsel__new_idx (&attr, evlist->core.nr_entries); +} + +int evlist__add_dummy (struct evlist *evlist) +{ +struct evsel *evsel =evlist__dummy_event (evlist);if (evsel ==NULL )return -ENOMEM ; --2.25.1
Adrian Hunter
reviewerPATCH 13/23 perf evlist: Add evlist__add_system_wide_dummy()
In reply to Adrian HunterAdd evlist__add_system_wide_dummy() to enable creating a system-wide dummy event that sets up the system-wide maps before map propagation.
For convenience, add evlist__add_aux_dummy() so that the logic can be used whether or not the event needs to be system-wide.
--- tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 5 +++++ 2 files changed, 45 insertions(+)
tools/perf/util/evlist.c +40 -0
@@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)return 0 ; } +static void evlist__add_system_wide (struct evlist *evlist,struct evsel *evsel) +{ + evsel->core.system_wide = true; + +/* All CPUs */ +perf_cpu_map__put (evsel->core.own_cpus); + evsel->core.own_cpus =perf_cpu_map__new (NULL ); +perf_cpu_map__put (evsel->core.cpus); + evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); + +/* No threads */ +perf_thread_map__put (evsel->core.threads); + evsel->core.threads =perf_thread_map__new_dummy (); + +evlist__add (evlist, evsel); +} + +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide) +{ +struct evsel *evsel =evlist__dummy_event (evlist); + +if (!evsel) +return NULL ; + + evsel->core.attr.exclude_kernel =1 ; + evsel->core.attr.exclude_guest =1 ; + evsel->core.attr.exclude_hv =1 ; + evsel->core.attr.freq =0 ; + evsel->core.attr.sample_period =1 ; + evsel->no_aux_samples = true; + evsel->name =strdup ("dummy:u" ); + +if (system_wide) +evlist__add_system_wide (evlist, evsel); +else +evlist__add (evlist, evsel); + +return evsel; +} +static int evlist__add_attrs (struct evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs) {struct evsel *evsel, *n;
tools/perf/util/evlist.h +5 -0
@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);struct evsel *arch_evlist__leader (struct list_head *list);int evlist__add_dummy (struct evlist *evlist); +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide); +static inline struct evsel *evlist__add_system_wide_dummy (struct evlist *evlist) +{ +return evlist__add_aux_dummy (evlist, true); +}int evlist__add_sb_event (struct evlist *evlist,struct perf_event_attr *attr,evsel__sb_cb_t cb,void *data);
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy()
Quoted 3 lines · Adrian Hunter
Add
evlist__add_system_wide_dummy()to enable creating a system-wide dummy event that sets up the system-wide maps before map propagation.
Perhaps this should be:evlist__add_dummy_on_all_online_cpus()
my thoughts being that a system wide dummy sounds like the dummy CPU map, ie {-1} whilst what happens here is opening on all online CPUs {0-35} on a 36 hyperthread system. Note also that the libperf cpu_map__read_all_cpu_map code doesn't discover sysfs' mount properly, as done in:tools/lib/api/fs/fs.h
Some tech debt.
Quoted 14 lines
For convenience, add
evlist__add_aux_dummy()so that the logic can be used whether or not the event needs to be system-wide.Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 5 +++++ 2 files changed, 45 insertions(+)tools/perf/util/evlist.c +0
-0
tools/perf/util/evlist.c int evlist__add_dummy(struct evlist *evlist) · line 267
Quoted 4 lines
tools/perf/util/evlist.c +1
-0@@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)return 0 ; } +static void evlist__add_system_wide (struct evlist *evlist,struct evsel *evsel)
This would be:evlist__add_on_all_online_cpus(..)
Quoted 61 lines
tools/perf/util/evlist.c +39
-0+{ + evsel->core.system_wide = true; + +/* All CPUs */ +perf_cpu_map__put (evsel->core.own_cpus); + evsel->core.own_cpus =perf_cpu_map__new (NULL ); +perf_cpu_map__put (evsel->core.cpus); + evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); + +/* No threads */ +perf_thread_map__put (evsel->core.threads); + evsel->core.threads =perf_thread_map__new_dummy (); + +evlist__add (evlist, evsel); +} + +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide) +{ +struct evsel *evsel =evlist__dummy_event (evlist); + +if (!evsel) +return NULL ; + + evsel->core.attr.exclude_kernel =1 ; + evsel->core.attr.exclude_guest =1 ; + evsel->core.attr.exclude_hv =1 ; + evsel->core.attr.freq =0 ; + evsel->core.attr.sample_period =1 ; + evsel->no_aux_samples = true; + evsel->name =strdup ("dummy:u" ); + +if (system_wide) +evlist__add_system_wide (evlist, evsel); +else +evlist__add (evlist, evsel); + +return evsel; +} +static int evlist__add_attrs (struct evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs) {struct evsel *evsel, *n;tools/perf/util/evlist.h +5
-1@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);struct evsel *arch_evlist__leader (struct list_head *list);int evlist__add_dummy (struct evlist *evlist); +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide); +static inline struct evsel *evlist__add_system_wide_dummy (struct evlist *evlist) +{ +return evlist__add_aux_dummy (evlist, true); +}int evlist__add_sb_event (struct evlist *evlist,struct perf_event_attr *attr,evsel__sb_cb_t cb,void *data); --2.25.1
Adrian Hunter
reviewerRe: [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy()
Quoted 7 lines · Ian Rogers
Quoted 3 lines · Adrian Hunter
Add
evlist__add_system_wide_dummy()to enable creating a system-wide dummy event that sets up the system-wide maps before map propagation.Perhaps this should be:
evlist__add_dummy_on_all_online_cpus()
Ok, but offline isn't an option, so I'll drop 'online' from the name.
Quoted 91 lines
my thoughts being that a system wide dummy sounds like the dummy CPU map, ie {-1} whilst what happens here is opening on all online CPUs {0-35} on a 36 hyperthread system. Note also that the libperf
cpu_map__read_all_cpu_mapcode doesn't discover sysfs' mount properly, as done in:tools/lib/api/fs/fs.h
Some tech debt.Quoted 14 lines
For convenience, add
evlist__add_aux_dummy()so that the logic can be used whether or not the event needs to be system-wide.Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 5 +++++ 2 files changed, 45 insertions(+)tools/perf/util/evlist.c +0
-0tools/perf/util/evlist.c int evlist__add_dummy(struct evlist *evlist) · line 267
Quoted 4 lines
tools/perf/util/evlist.c +1
-0@@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)return 0 ; } +static void evlist__add_system_wide (struct evlist *evlist,struct evsel *evsel)This would be:
evlist__add_on_all_online_cpus(..)Quoted 61 lines
tools/perf/util/evlist.c +39
-0+{ + evsel->core.system_wide = true; + +/* All CPUs */ +perf_cpu_map__put (evsel->core.own_cpus); + evsel->core.own_cpus =perf_cpu_map__new (NULL ); +perf_cpu_map__put (evsel->core.cpus); + evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); + +/* No threads */ +perf_thread_map__put (evsel->core.threads); + evsel->core.threads =perf_thread_map__new_dummy (); + +evlist__add (evlist, evsel); +} + +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide) +{ +struct evsel *evsel =evlist__dummy_event (evlist); + +if (!evsel) +return NULL ; + + evsel->core.attr.exclude_kernel =1 ; + evsel->core.attr.exclude_guest =1 ; + evsel->core.attr.exclude_hv =1 ; + evsel->core.attr.freq =0 ; + evsel->core.attr.sample_period =1 ; + evsel->no_aux_samples = true; + evsel->name =strdup ("dummy:u" ); + +if (system_wide) +evlist__add_system_wide (evlist, evsel); +else +evlist__add (evlist, evsel); + +return evsel; +} +static int evlist__add_attrs (struct evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs) {struct evsel *evsel, *n;tools/perf/util/evlist.h +5
-1@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);struct evsel *arch_evlist__leader (struct list_head *list);int evlist__add_dummy (struct evlist *evlist); +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide); +static inline struct evsel *evlist__add_system_wide_dummy (struct evlist *evlist) +{ +return evlist__add_aux_dummy (evlist, true); +}int evlist__add_sb_event (struct evlist *evlist,struct perf_event_attr *attr,evsel__sb_cb_t cb,void *data); --2.25.1
Ian Rogers
reviewerRe: [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy()
Quoted 11 lines · Adrian Hunter
Quoted 7 lines · Ian Rogers
Quoted 3 lines · Adrian Hunter
Add
evlist__add_system_wide_dummy()to enable creating a system-wide dummy event that sets up the system-wide maps before map propagation.Perhaps this should be:
evlist__add_dummy_on_all_online_cpus()Ok, but offline isn't an option, so I'll drop 'online' from the name.
I'm not sure I follow. There can be CPUs that are offline (echo 0 > /sys/devices/system/cpu/cpu2/online) and then brought online while perf is running. The output obviously won't be right as we're missing dummy events. Losing online from the name here seems to remove a useful clue.
Thanks,
Ian
Quoted 92 lines
Quoted 91 lines
my thoughts being that a system wide dummy sounds like the dummy CPU map, ie {-1} whilst what happens here is opening on all online CPUs {0-35} on a 36 hyperthread system. Note also that the libperf
cpu_map__read_all_cpu_mapcode doesn't discover sysfs' mount properly, as done in:tools/lib/api/fs/fs.h
Some tech debt.Quoted 14 lines
For convenience, add
evlist__add_aux_dummy()so that the logic can be used whether or not the event needs to be system-wide.Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 5 +++++ 2 files changed, 45 insertions(+)tools/perf/util/evlist.c +0
-0tools/perf/util/evlist.c int evlist__add_dummy(struct evlist *evlist) · line 267
Quoted 4 lines
tools/perf/util/evlist.c +1
-0@@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)return 0 ; } +static void evlist__add_system_wide (struct evlist *evlist,struct evsel *evsel)This would be:
evlist__add_on_all_online_cpus(..)Quoted 61 lines
tools/perf/util/evlist.c +39
-0+{ + evsel->core.system_wide = true; + +/* All CPUs */ +perf_cpu_map__put (evsel->core.own_cpus); + evsel->core.own_cpus =perf_cpu_map__new (NULL ); +perf_cpu_map__put (evsel->core.cpus); + evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); + +/* No threads */ +perf_thread_map__put (evsel->core.threads); + evsel->core.threads =perf_thread_map__new_dummy (); + +evlist__add (evlist, evsel); +} + +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide) +{ +struct evsel *evsel =evlist__dummy_event (evlist); + +if (!evsel) +return NULL ; + + evsel->core.attr.exclude_kernel =1 ; + evsel->core.attr.exclude_guest =1 ; + evsel->core.attr.exclude_hv =1 ; + evsel->core.attr.freq =0 ; + evsel->core.attr.sample_period =1 ; + evsel->no_aux_samples = true; + evsel->name =strdup ("dummy:u" ); + +if (system_wide) +evlist__add_system_wide (evlist, evsel); +else +evlist__add (evlist, evsel); + +return evsel; +} +static int evlist__add_attrs (struct evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs) {struct evsel *evsel, *n;tools/perf/util/evlist.h +5
-1@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);struct evsel *arch_evlist__leader (struct list_head *list);int evlist__add_dummy (struct evlist *evlist); +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide); +static inline struct evsel *evlist__add_system_wide_dummy (struct evlist *evlist) +{ +return evlist__add_aux_dummy (evlist, true); +}int evlist__add_sb_event (struct evlist *evlist,struct perf_event_attr *attr,evsel__sb_cb_t cb,void *data); --2.25.1
Adrian Hunter
reviewerRe: [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy()
Quoted 11 lines · Ian Rogers
Quoted 10 lines · Adrian Hunter
Quoted 7 lines · Ian Rogers
Quoted 3 lines · Adrian Hunter
Add
evlist__add_system_wide_dummy()to enable creating a system-wide dummy event that sets up the system-wide maps before map propagation.Perhaps this should be:
evlist__add_dummy_on_all_online_cpus()
Quoted 7 lines
Quoted 1 line
Ok, but offline isn't an option, so I'll drop 'online' from the name.
I'm not sure I follow. There can be CPUs that are offline (echo 0 >
/sys/devices/system/cpu/cpu2/online) and then brought online while perf is running. The output obviously won't be right as we're missing dummy events. Losing online from the name here seems to remove a useful clue.
perf_event_open() will not accept events on offline CPUs.
Quoted 96 lines
Thanks,
IanQuoted 92 lines
Quoted 91 lines
my thoughts being that a system wide dummy sounds like the dummy CPU map, ie {-1} whilst what happens here is opening on all online CPUs {0-35} on a 36 hyperthread system. Note also that the libperf
cpu_map__read_all_cpu_mapcode doesn't discover sysfs' mount properly, as done in:tools/lib/api/fs/fs.h
Some tech debt.Quoted 14 lines
For convenience, add
evlist__add_aux_dummy()so that the logic can be used whether or not the event needs to be system-wide.Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 5 +++++ 2 files changed, 45 insertions(+)tools/perf/util/evlist.c +0
-0tools/perf/util/evlist.c int evlist__add_dummy(struct evlist *evlist) · line 267
Quoted 4 lines
tools/perf/util/evlist.c +1
-0@@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)return 0 ; } +static void evlist__add_system_wide (struct evlist *evlist,struct evsel *evsel)This would be:
evlist__add_on_all_online_cpus(..)Quoted 61 lines
tools/perf/util/evlist.c +39
-0+{ + evsel->core.system_wide = true; + +/* All CPUs */ +perf_cpu_map__put (evsel->core.own_cpus); + evsel->core.own_cpus =perf_cpu_map__new (NULL ); +perf_cpu_map__put (evsel->core.cpus); + evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); + +/* No threads */ +perf_thread_map__put (evsel->core.threads); + evsel->core.threads =perf_thread_map__new_dummy (); + +evlist__add (evlist, evsel); +} + +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide) +{ +struct evsel *evsel =evlist__dummy_event (evlist); + +if (!evsel) +return NULL ; + + evsel->core.attr.exclude_kernel =1 ; + evsel->core.attr.exclude_guest =1 ; + evsel->core.attr.exclude_hv =1 ; + evsel->core.attr.freq =0 ; + evsel->core.attr.sample_period =1 ; + evsel->no_aux_samples = true; + evsel->name =strdup ("dummy:u" ); + +if (system_wide) +evlist__add_system_wide (evlist, evsel); +else +evlist__add (evlist, evsel); + +return evsel; +} +static int evlist__add_attrs (struct evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs) {struct evsel *evsel, *n;tools/perf/util/evlist.h +5
-1@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);struct evsel *arch_evlist__leader (struct list_head *list);int evlist__add_dummy (struct evlist *evlist); +struct evsel *evlist__add_aux_dummy (struct evlist *evlist,bool system_wide); +static inline struct evsel *evlist__add_system_wide_dummy (struct evlist *evlist) +{ +return evlist__add_aux_dummy (evlist, true); +}int evlist__add_sb_event (struct evlist *evlist,struct perf_event_attr *attr,evsel__sb_cb_t cb,void *data); --2.25.1
Adrian Hunter
reviewerPATCH 14/23 perf record: Use evlist__add_system_wide_dummy() in record__config_text_poke()
In reply to Adrian HunterUse evlist__add_system_wide_dummy() in record__config_text_poke() in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.
--- tools/perf/builtin-record.c | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-)
tools/perf/builtin-record.c +3 -18
@@ -869,7 +869,6 @@ static int record__auxtrace_init(struct record *rec __maybe_unused)static int record__config_text_poke (struct evlist *evlist) {struct evsel *evsel; -int err;/* Nothing to do if text poke is already configured */ evlist__for_each_entry (evlist, evsel) {
@@ -877,27 +876,13 @@ static int record__config_text_poke(struct evlist *evlist)return 0 ; } - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; - - evsel =evlist__last (evlist); + evsel =evlist__add_system_wide_dummy (evlist); +if (!evsel) +return -ENOMEM ; - evsel->core.attr.freq =0 ; - evsel->core.attr.sample_period =1 ; evsel->core.attr.text_poke =1 ; evsel->core.attr.ksymbol =1 ; - - evsel->core.system_wide = true; - evsel->no_aux_samples = true; evsel->immediate = true; - -/* Text poke must be collected on all CPUs */ -perf_cpu_map__put (evsel->core.own_cpus); - evsel->core.own_cpus =perf_cpu_map__new (NULL ); -perf_cpu_map__put (evsel->core.cpus); - evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); -evsel__set_sample_bit (evsel,TIME );return 0 ;
Signature · 1 line
2.25.1
Re: [PATCH V1 14/23] perf record: Use evlist__add_system_wide_dummy() in record__config_text_poke()
Quoted 6 lines · Adrian Hunter
Use
evlist__add_system_wide_dummy()inrecord__config_text_poke()in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.Signed-off-by Adrian Hunter <[email protected]>
Delta function names.
Thanks,
Ian
Quoted 50 lines
--- tools/perf/builtin-record.c | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-)tools/perf/builtin-record.c +3
-19@@ -869,7 +869,6 @@ static int record__auxtrace_init(struct record *rec __maybe_unused)static int record__config_text_poke (struct evlist *evlist) {struct evsel *evsel; -int err;/* Nothing to do if text poke is already configured */ evlist__for_each_entry (evlist, evsel) {@@ -877,27 +876,13 @@ static int record__config_text_poke(struct evlist *evlist)return 0 ; } - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; - - evsel =evlist__last (evlist); + evsel =evlist__add_system_wide_dummy (evlist); +if (!evsel) +return -ENOMEM ; - evsel->core.attr.freq =0 ; - evsel->core.attr.sample_period =1 ; evsel->core.attr.text_poke =1 ; evsel->core.attr.ksymbol =1 ; - - evsel->core.system_wide = true; - evsel->no_aux_samples = true; evsel->immediate = true; - -/* Text poke must be collected on all CPUs */ -perf_cpu_map__put (evsel->core.own_cpus); - evsel->core.own_cpus =perf_cpu_map__new (NULL ); -perf_cpu_map__put (evsel->core.cpus); - evsel->core.cpus =perf_cpu_map__get (evsel->core.own_cpus); -evsel__set_sample_bit (evsel,TIME );return 0 ; --2.25.1
Adrian Hunter
reviewerPATCH 15/23 perf intel-pt: Use evlist__add_system_wide_dummy() for switch tracking
In reply to Adrian HunterUse evlist__add_system_wide_dummy() for switch tracking in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.
--- tools/perf/arch/x86/util/intel-pt.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-)
tools/perf/arch/x86/util/intel-pt.c +3 -10
@@ -811,18 +811,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,if (!cpu_wide &&perf_can_record_cpu_wide ()) {struct evsel *switch_evsel; - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; + switch_evsel =evlist__add_system_wide_dummy (evlist); +if (!switch_evsel) +return -ENOMEM ; - switch_evsel =evlist__last (evlist); - - switch_evsel->core.attr.freq =0 ; - switch_evsel->core.attr.sample_period =1 ; switch_evsel->core.attr.context_switch =1 ; - - switch_evsel->core.system_wide = true; - switch_evsel->no_aux_samples = true; switch_evsel->immediate = true;evsel__set_sample_bit (switch_evsel,TID );
Signature · 1 line
2.25.1
Re: [PATCH V1 15/23] perf intel-pt: Use evlist__add_system_wide_dummy() for switch tracking
Quoted 6 lines · Adrian Hunter
Use
evlist__add_system_wide_dummy()for switch tracking in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.Signed-off-by Adrian Hunter <[email protected]>
Delta function names.
Thanks,
Ian
Quoted 33 lines
--- tools/perf/arch/x86/util/intel-pt.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-)tools/perf/arch/x86/util/intel-pt.c +3
-11@@ -811,18 +811,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,if (!cpu_wide &&perf_can_record_cpu_wide ()) {struct evsel *switch_evsel; - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; + switch_evsel =evlist__add_system_wide_dummy (evlist); +if (!switch_evsel) +return -ENOMEM ; - switch_evsel =evlist__last (evlist); - - switch_evsel->core.attr.freq =0 ; - switch_evsel->core.attr.sample_period =1 ; switch_evsel->core.attr.context_switch =1 ; - - switch_evsel->core.system_wide = true; - switch_evsel->no_aux_samples = true; switch_evsel->immediate = true;evsel__set_sample_bit (switch_evsel,TID ); --2.25.1
Adrian Hunter
reviewerPATCH 16/23 perf intel-pt: Track sideband system-wide when needed
In reply to Adrian HunterUser space tasks can migrate between CPUs, so when tracing selected CPUs, sideband for all CPUs is still needed. This is in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.
--- tools/perf/arch/x86/util/intel-pt.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
tools/perf/arch/x86/util/intel-pt.c +10 -8
@@ -864,20 +864,22 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,/* Add dummy event to keep tracking */ if (opts->full_auxtrace) { +bool need_system_wide_tracking;struct evsel *tracking_evsel; - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; +/* +* User space tasks can migrate between CPUs, so when tracing +* selected CPUs, sideband for all CPUs is still needed. +*/ + need_system_wide_tracking = evlist->core.has_user_cpus && + !intel_pt_evsel->core.attr.exclude_user; - tracking_evsel =evlist__last (evlist); + tracking_evsel =evlist__add_aux_dummy (evlist, need_system_wide_tracking); +if (!tracking_evsel) +return -ENOMEM ;evlist__set_tracking_event (evlist, tracking_evsel); - tracking_evsel->core.attr.freq =0 ; - tracking_evsel->core.attr.sample_period =1 ; - - tracking_evsel->no_aux_samples = true;if (need_immediate) tracking_evsel->immediate = true;
Signature · 1 line
2.25.1
Re: [PATCH V1 16/23] perf intel-pt: Track sideband system-wide when needed
Quoted 16 lines · Adrian Hunter
User space tasks can migrate between CPUs, so when tracing selected CPUs, sideband for all CPUs is still needed. This is in preparation for allowing system-wide events on all CPUs while the user requested events are on only user requested CPUs.
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/arch/x86/util/intel-pt.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)tools/perf/arch/x86/util/intel-pt.c +0
-0
tools/perf/arch/x86/util/intel-pt.c static int intel_pt_recording_options(struct auxtrace_record *itr, · line 867
Quoted 4 lines
tools/perf/arch/x86/util/intel-pt.c +1
-0@@ -864,20 +864,22 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,/* Add dummy event to keep tracking */ if (opts->full_auxtrace) { +bool need_system_wide_tracking;
Nit: perhaps need_dummy_on_all_online_cpus
Thanks,
Ian
Quoted 29 lines
tools/perf/arch/x86/util/intel-pt.c +9
-9struct evsel *tracking_evsel; - err =parse_events (evlist,"dummy:u" ,NULL ); -if (err) -return err; +/* +* User space tasks can migrate between CPUs, so when tracing +* selected CPUs, sideband for all CPUs is still needed. +*/ + need_system_wide_tracking = evlist->core.has_user_cpus && + !intel_pt_evsel->core.attr.exclude_user; - tracking_evsel =evlist__last (evlist); + tracking_evsel =evlist__add_aux_dummy (evlist, need_system_wide_tracking); +if (!tracking_evsel) +return -ENOMEM ;evlist__set_tracking_event (evlist, tracking_evsel); - tracking_evsel->core.attr.freq =0 ; - tracking_evsel->core.attr.sample_period =1 ; - - tracking_evsel->no_aux_samples = true;if (need_immediate) tracking_evsel->immediate = true; --2.25.1
Adrian Hunter
reviewerPATCH 17/23 perf tools: Allow all_cpus to be a superset of user_requested_cpus
In reply to Adrian HunterTo support collection of system-wide events with user requested CPUs, all_cpus must be a superset of user_requested_cpus.
In order to support all_cpus to be a superset of user_requested_cpus, all_cpus must be used instead of user_requested_cpus when dealing with CPUs of all events instead of CPUs of requested events.
--- tools/lib/perf/evlist.c | 12 ++++++------ tools/perf/builtin-record.c | 18 ++++++++++++------ tools/perf/util/auxtrace.c | 2 +- 3 files changed, 19 insertions(+), 13 deletions(-)
tools/lib/perf/evlist.c +6 -6
@@ -294,7 +294,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,int perf_evlist__alloc_pollfd (struct perf_evlist *evlist) { -int nr_cpus =perf_cpu_map__nr (evlist->user_requested_cpus); +int nr_cpus =perf_cpu_map__nr (evlist->all_cpus);int nr_threads =perf_thread_map__nr (evlist->threads);int nfds =0 ;struct perf_evsel *evsel;
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int idx, struct perf_mmap_param *mp, int cpu_idx, int thread, int *_output, int *_output_overwrite) { - struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx);struct perf_evsel *evsel;int revent;
@@ -536,7 +536,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) {int nr_threads =perf_thread_map__nr (evlist->threads); -int nr_cpus =perf_cpu_map__nr (evlist->user_requested_cpus); +int nr_cpus =perf_cpu_map__nr (evlist->all_cpus);int cpu, thread;for (cpu =0 ; cpu < nr_cpus; cpu++) {
@@ -561,8 +561,8 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) {int nr_mmaps; - nr_mmaps =perf_cpu_map__nr (evlist->user_requested_cpus); -if (perf_cpu_map__empty (evlist->user_requested_cpus)) + nr_mmaps =perf_cpu_map__nr (evlist->all_cpus); +if (perf_cpu_map__empty (evlist->all_cpus)) nr_mmaps =perf_thread_map__nr (evlist->threads);return nr_mmaps;
@@ -573,7 +573,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_mmap_param *mp) {struct perf_evsel *evsel; -const struct perf_cpu_map *cpus = evlist->user_requested_cpus; +const struct perf_cpu_map *cpus = evlist->all_cpus;if (!ops || !ops->get || !ops->mmap)return -EINVAL ;
tools/perf/builtin-record.c +12 -6
@@ -967,14 +967,20 @@ static void record__thread_data_close_pipes(struct record_thread *thread_data) } } +static bool evlist__per_thread (struct evlist *evlist) +{ +return cpu_map__is_dummy (evlist->core.user_requested_cpus); +} +static int record__thread_data_init_maps (struct record_thread *thread_data,struct evlist *evlist) {int m, tm, nr_mmaps = evlist->core.nr_mmaps;struct mmap *mmap = evlist->mmap;struct mmap *overwrite_mmap = evlist->overwrite_mmap; -struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; +struct perf_cpu_map *cpus = evlist->core.all_cpus; +bool per_thread =evlist__per_thread (evlist); -if (cpu_map__is_dummy (cpus)) +if (per_thread) thread_data->nr_mmaps = nr_mmaps;else thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
@@ -995,7 +1001,7 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);for (m =0 , tm =0 ; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { -if (cpu_map__is_dummy (cpus) || +if (per_thread ||test_bit (cpus->map[m].cpu, thread_data->mask->maps.bits)) {if (thread_data->maps) { thread_data->maps[tm] = &mmap[m];
@@ -1870,7 +1876,7 @@ static int record__synthesize(struct record *rec, bool tail)return err; } - err =perf_event__synthesize_cpu_map (&rec->tool, rec->evlist->core.user_requested_cpus, + err =perf_event__synthesize_cpu_map (&rec->tool, rec->evlist->core.all_cpus, process_synthesized_event,NULL );if (err <0 ) {pr_err ("Couldn't synthesize cpu map.\n" );
@@ -3667,12 +3673,12 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpustatic int record__init_thread_masks (struct record *rec) {int ret =0 ; -struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus; +struct perf_cpu_map *cpus = rec->evlist->core.all_cpus;if (!record__threads_enabled (rec))return record__init_thread_default_masks (rec, cpus); -if (cpu_map__is_dummy (cpus)) { +if (evlist__per_thread (rec->evlist)) {pr_err ("--per-thread option is mutually exclusive to parallel streaming mode.\n" );return -EINVAL ; }
tools/perf/util/auxtrace.c +1 -1
@@ -181,7 +181,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, mp->idx = idx;if (per_cpu) { - mp->cpu =perf_cpu_map__cpu (evlist->core.user_requested_cpus, idx); + mp->cpu =perf_cpu_map__cpu (evlist->core.all_cpus, idx);if (evlist->core.threads) mp->tid =perf_thread_map__pid (evlist->core.threads,0 );else
Signature · 1 line
2.25.1
Adrian Hunter
reviewerPATCH 18/23 libperf evlist: Allow mixing per-thread and per-cpu mmaps
In reply to Adrian Huntermmap_per_evsel() will skip events that do not match the CPU, so all CPUs can be iterated in any case.
--- tools/lib/perf/evlist.c | 36 +++++++----------------------------- 1 file changed, 7 insertions(+), 29 deletions(-)
tools/lib/perf/evlist.c +7 -29
@@ -508,29 +508,6 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,return 0 ; } -static int -mmap_per_thread (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops, -struct perf_mmap_param *mp) -{ -int thread; -int nr_threads =perf_thread_map__nr (evlist->threads); - -for (thread =0 ; thread < nr_threads; thread++) { -int output =-1 ; -int output_overwrite =-1 ; - -if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, - &output, &output_overwrite)) - goto out_unmap; - } - -return 0 ; - -out_unmap: -perf_evlist__munmap (evlist); -return -1 ; -} -static int mmap_per_cpu (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops,struct perf_mmap_param *mp)
@@ -561,9 +538,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) {int nr_mmaps; +/* One for each CPU */ nr_mmaps =perf_cpu_map__nr (evlist->all_cpus); -if (perf_cpu_map__empty (evlist->all_cpus)) - nr_mmaps =perf_thread_map__nr (evlist->threads); +if (perf_cpu_map__empty (evlist->all_cpus)) { +/* Plus one for each thread */ + nr_mmaps +=perf_thread_map__nr (evlist->threads); +/* Minus the per-thread CPU (-1) */ + nr_mmaps -=1 ; + }return nr_mmaps; }
@@ -573,7 +555,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_mmap_param *mp) {struct perf_evsel *evsel; -const struct perf_cpu_map *cpus = evlist->all_cpus;if (!ops || !ops->get || !ops->mmap)return -EINVAL ;
@@ -592,9 +573,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,if (evlist->pollfd.entries ==NULL &&perf_evlist__alloc_pollfd (evlist) <0 )return -ENOMEM ; -if (perf_cpu_map__empty (cpus)) -return mmap_per_thread (evlist, ops, mp); -return mmap_per_cpu (evlist, ops, mp); }
Signature · 1 line
2.25.1
Re: [PATCH V1 18/23] libperf evlist: Allow mixing per-thread and per-cpu mmaps
Quoted 5 lines · Adrian Hunter
mmap_per_evsel()will skip events that do not match the CPU, so all CPUs can be iterated in any case.Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 39 lines
--- tools/lib/perf/evlist.c | 36 +++++++----------------------------- 1 file changed, 7 insertions(+), 29 deletions(-)tools/lib/perf/evlist.c +0
-23@@ -508,29 +508,6 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,return 0 ; } -static int -mmap_per_thread (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops, -struct perf_mmap_param *mp) -{ -int thread; -int nr_threads =perf_thread_map__nr (evlist->threads); - -for (thread =0 ; thread < nr_threads; thread++) { -int output =-1 ; -int output_overwrite =-1 ; - -if (mmap_per_evsel (evlist, ops, thread, mp,0 , thread, - &output, &output_overwrite)) - goto out_unmap; - } - -return 0 ; - -out_unmap: -perf_evlist__munmap (evlist); -return -1 ; -} -static int mmap_per_cpu (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops,struct perf_mmap_param *mp)
tools/lib/perf/evlist.c static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) · line 543
Quoted 8 lines
tools/lib/perf/evlist.c +2
-2@@ -561,9 +538,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) {int nr_mmaps; +/* One for each CPU */ nr_mmaps =perf_cpu_map__nr (evlist->all_cpus); -if (perf_cpu_map__empty (evlist->all_cpus)) - nr_mmaps =perf_thread_map__nr (evlist->threads); +if (perf_cpu_map__empty (evlist->all_cpus)) {
Here with the current definition of perf_cpu_map__empty this is a NULL or first element is any CPU (aka dummy) test. Given our conversation this may not work as intended for that definition.
Quoted 29 lines
tools/lib/perf/evlist.c +5
-5+/* Plus one for each thread */ + nr_mmaps +=perf_thread_map__nr (evlist->threads); +/* Minus the per-thread CPU (-1) */ + nr_mmaps -=1 ; + }return nr_mmaps; }@@ -573,7 +555,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_mmap_param *mp) {struct perf_evsel *evsel; -const struct perf_cpu_map *cpus = evlist->all_cpus;if (!ops || !ops->get || !ops->mmap)return -EINVAL ;@@ -592,9 +573,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,if (evlist->pollfd.entries ==NULL &&perf_evlist__alloc_pollfd (evlist) <0 )return -ENOMEM ; -if (perf_cpu_map__empty (cpus)) -return mmap_per_thread (evlist, ops, mp); -return mmap_per_cpu (evlist, ops, mp); } --2.25.1
Adrian Hunter
reviewerPATCH 19/23 libperf evlist: Check nr_mmaps is correct
In reply to Adrian HunterPrint an error message if the predetermined number of mmaps is incorrect.
--- tools/lib/perf/evlist.c | 11 +++++++++-- tools/lib/perf/include/internal/mmap.h | 5 +++++ 2 files changed, 14 insertions(+), 2 deletions(-)
tools/lib/perf/evlist.c +9 -2
@@ -23,6 +23,7 @@#include <perf/cpumap.h> #include <perf/threadmap.h> #include <api/fd/array.h> +#include "internal.h" void perf_evlist__init (struct perf_evlist *evlist) {
@@ -424,7 +425,7 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_static int mmap_per_evsel (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops,int idx,struct perf_mmap_param *mp,int cpu_idx, -int thread,int *_output,int *_output_overwrite) +int thread,int *_output,int *_output_overwrite,int *nr_mmaps) {struct perf_cpu evlist_cpu =perf_cpu_map__cpu (evlist->all_cpus, cpu_idx);struct perf_evsel *evsel;
@@ -480,6 +481,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ; + *nr_mmaps +=1 ; +if (!idx)perf_evlist__set_mmap_first (evlist, map, overwrite); }else {
@@ -514,6 +517,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, {int nr_threads =perf_thread_map__nr (evlist->threads);int nr_cpus =perf_cpu_map__nr (evlist->all_cpus); +int nr_mmaps =0 ;int cpu, thread;for (cpu =0 ; cpu < nr_cpus; cpu++) {
@@ -522,11 +526,14 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,for (thread =0 ; thread < nr_threads; thread++) {if (mmap_per_evsel (evlist, ops, cpu, mp, cpu, - thread, &output, &output_overwrite)) + thread, &output, &output_overwrite, &nr_mmaps)) goto out_unmap; } } +if (nr_mmaps != evlist->nr_mmaps) +pr_err ("Miscounted nr_mmaps %d vs %d\n" , nr_mmaps, evlist->nr_mmaps); +return 0 ; out_unmap:
tools/lib/perf/include/internal/mmap.h +5 -0
@@ -56,4 +56,9 @@ u64 perf_mmap__read_head(struct perf_mmap *map);int perf_mmap__read_self (struct perf_mmap *map,struct perf_counts_values *count); +static inline bool perf_mmap__is_mmapped (struct perf_mmap *map) +{ +return map->base; +} +#endif /* __LIBPERF_INTERNAL_MMAP_H */
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 19/23] libperf evlist: Check nr_mmaps is correct
Quoted 69 lines · Adrian Hunter
Print an error message if the predetermined number of mmaps is incorrect.
Signed-off-by Adrian Hunter <[email protected]>--- tools/lib/perf/evlist.c | 11 +++++++++-- tools/lib/perf/include/internal/mmap.h | 5 +++++ 2 files changed, 14 insertions(+), 2 deletions(-)tools/lib/perf/evlist.c +9
-2@@ -23,6 +23,7 @@#include <perf/cpumap.h> #include <perf/threadmap.h> #include <api/fd/array.h> +#include "internal.h" void perf_evlist__init (struct perf_evlist *evlist) {@@ -424,7 +425,7 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_static int mmap_per_evsel (struct perf_evlist *evlist,struct perf_evlist_mmap_ops *ops,int idx,struct perf_mmap_param *mp,int cpu_idx, -int thread,int *_output,int *_output_overwrite) +int thread,int *_output,int *_output_overwrite,int *nr_mmaps) {struct perf_cpu evlist_cpu =perf_cpu_map__cpu (evlist->all_cpus, cpu_idx);struct perf_evsel *evsel;@@ -480,6 +481,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,if (ops->mmap (map, mp, *output, evlist_cpu) <0 )return -1 ; + *nr_mmaps +=1 ; +if (!idx)perf_evlist__set_mmap_first (evlist, map, overwrite); }else {@@ -514,6 +517,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, {int nr_threads =perf_thread_map__nr (evlist->threads);int nr_cpus =perf_cpu_map__nr (evlist->all_cpus); +int nr_mmaps =0 ;int cpu, thread;for (cpu =0 ; cpu < nr_cpus; cpu++) {@@ -522,11 +526,14 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,for (thread =0 ; thread < nr_threads; thread++) {if (mmap_per_evsel (evlist, ops, cpu, mp, cpu, - thread, &output, &output_overwrite)) + thread, &output, &output_overwrite, &nr_mmaps)) goto out_unmap; } } +if (nr_mmaps != evlist->nr_mmaps) +pr_err ("Miscounted nr_mmaps %d vs %d\n" , nr_mmaps, evlist->nr_mmaps); +return 0 ; out_unmap:tools/lib/perf/include/internal/mmap.h +0
-0
tools/lib/perf/include/internal/mmap.h u64 perf_mmap__read_head(struct perf_mmap *map); · line 63
Quoted 8 lines
tools/lib/perf/include/internal/mmap.h +5
-0@@ -56,4 +56,9 @@ u64 perf_mmap__read_head(struct perf_mmap *map);int perf_mmap__read_self (struct perf_mmap *map,struct perf_counts_values *count); +static inline bool perf_mmap__is_mmapped (struct perf_mmap *map) +{ +return map->base; +} +
This function is added here but not actually used by the patch.
Thanks,
Ian
Quoted 4 lines
tools/lib/perf/include/internal/mmap.h +0
-1#endif /* __LIBPERF_INTERNAL_MMAP_H */ --2.25.1
Adrian Hunter
reviewerPATCH 20/23 perf stat: Add requires_cpu flag for uncore
In reply to Adrian HunterUncore events require a CPU i.e. it cannot be -1.
The evsel system_wide flag is intended for events that should be on every CPU, which does not make sense for uncore events because uncore events do not map one-to-one with CPUs.
These 2 requirements are not exactly the same, so introduce a new flag 'requires_cpu' the uncore case.
--- tools/lib/perf/evlist.c | 4 +++- tools/lib/perf/include/internal/evsel.h | 1 + tools/perf/builtin-stat.c | 5 +---- tools/perf/util/evsel.c | 1 + tools/perf/util/parse-events.c | 2 +- 5 files changed, 7 insertions(+), 6 deletions(-)
tools/lib/perf/evlist.c +3 -1
@@ -43,7 +43,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,if (!evsel->own_cpus || evlist->has_user_cpus) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); - }else if (!evsel->system_wide &&perf_cpu_map__empty (evlist->user_requested_cpus)) { + }else if (!evsel->system_wide && + !evsel->requires_cpu && +perf_cpu_map__empty (evlist->user_requested_cpus)) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); }else if (evsel->cpus != evsel->own_cpus) {
tools/lib/perf/include/internal/evsel.h +1 -0
@@ -50,6 +50,7 @@ struct perf_evsel {/* parse modifier helper */ int nr_members;bool system_wide; +bool requires_cpu;int idx; };
tools/perf/builtin-stat.c +1 -4
@@ -385,9 +385,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_if (!counter->supported)return -ENOENT ; -if (counter->core.system_wide) - nthreads =1 ; -for (thread =0 ; thread < nthreads; thread++) {struct perf_counts_values *count;
@@ -2264,7 +2261,7 @@ static void setup_system_wide(int forks)struct evsel *counter;evlist__for_each_entry (evsel_list, counter) { -if (!counter->core.system_wide && +if (!counter->core.requires_cpu &&strcmp (counter->name,"duration_time" )) {return ; }
tools/perf/util/evsel.c +1 -0
@@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->core.threads =perf_thread_map__get (orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; + evsel->core.requires_cpu = orig->core.requires_cpu;if (orig->name) { evsel->name =strdup (orig->name);
tools/perf/util/parse-events.c +1 -1
@@ -365,7 +365,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->core.cpus = cpus; evsel->core.own_cpus =perf_cpu_map__get (cpus); - evsel->core.system_wide = pmu ? pmu->is_uncore : false; + evsel->core.requires_cpu = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats;if (name)
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 20/23] perf stat: Add requires_cpu flag for uncore
Quoted 9 lines · Adrian Hunter
Uncore events require a CPU i.e. it cannot be -1.
The evsel
system_wideflag is intended for events that should be on every CPU, which does not make sense for uncore events because uncore events do not map one-to-one with CPUs.These 2 requirements are not exactly the same, so introduce a new flag '
requires_cpu' the uncore case.
nit: typo missing 'for' the uncore case.
Quoted 29 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/lib/perf/evlist.c | 4 +++- tools/lib/perf/include/internal/evsel.h | 1 + tools/perf/builtin-stat.c | 5 +---- tools/perf/util/evsel.c | 1 + tools/perf/util/parse-events.c | 2 +- 5 files changed, 7 insertions(+), 6 deletions(-)tools/lib/perf/evlist.c +3
-1@@ -43,7 +43,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,if (!evsel->own_cpus || evlist->has_user_cpus) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); - }else if (!evsel->system_wide &&perf_cpu_map__empty (evlist->user_requested_cpus)) { + }else if (!evsel->system_wide && + !evsel->requires_cpu && +perf_cpu_map__empty (evlist->user_requested_cpus)) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); }else if (evsel->cpus != evsel->own_cpus) {tools/lib/perf/include/internal/evsel.h +0
-0
tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 51
Quoted 2 lines
tools/lib/perf/include/internal/evsel.h +0
-0@@ -50,6 +50,7 @@ struct perf_evsel {/* parse modifier helper */ int nr_members;
From the commit message, could we add the comment:
/* True for events that should be on every CPU. */
However, shouldn't this be captured by the CPU map? Perhaps we can have an invariant check that they agree.
tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 52
Quoted 1 line
tools/lib/perf/include/internal/evsel.h +0
-0bool system_wide;
/* True for events that cannot be the any CPU (-1), for example, uncore events. */
Quoted 19 lines
tools/lib/perf/include/internal/evsel.h +1
-0+bool requires_cpu;int idx; };tools/perf/builtin-stat.c +0
-3@@ -385,9 +385,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_if (!counter->supported)return -ENOENT ; -if (counter->core.system_wide) - nthreads =1 ; -for (thread =0 ; thread < nthreads; thread++) {struct perf_counts_values *count;
tools/perf/builtin-stat.c static void setup_system_wide(int forks) · line 2265
Quoted 6 lines
tools/perf/builtin-stat.c +1
-1@@ -2264,7 +2261,7 @@ static void setup_system_wide(int forks)struct evsel *counter;evlist__for_each_entry (evsel_list, counter) { -if (!counter->core.system_wide && +if (!counter->core.requires_cpu &&strcmp (counter->name,"duration_time" )) {
Off-topic of the patch: this test is a tool event check, it'd be better to do:
if (!counter->core.requires_cpu && counter->tool_event != PERF_TOOL_NONE)
Otherwise changes like:
https://lore.kernel.org/linux-perf-users/[email protected]/
Will break the test. I'll make a note to do a round of clean up.
Thanks,
Ian
Quoted 30 lines
tools/perf/builtin-stat.c +0
-0return ; }tools/perf/util/evsel.c +1
-0@@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->core.threads =perf_thread_map__get (orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; + evsel->core.requires_cpu = orig->core.requires_cpu;if (orig->name) { evsel->name =strdup (orig->name);tools/perf/util/parse-events.c +1
-2@@ -365,7 +365,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->core.cpus = cpus; evsel->core.own_cpus =perf_cpu_map__get (cpus); - evsel->core.system_wide = pmu ? pmu->is_uncore : false; + evsel->core.requires_cpu = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats;if (name) --2.25.1
Re: [PATCH V1 20/23] perf stat: Add requires_cpu flag for uncore
Quoted 5 lines · Ian Rogers
Quoted 3 lines · Adrian Hunter
Uncore events require a CPU i.e. it cannot be -1.
Quoted 10 lines
Quoted 6 lines
The evsel
system_wideflag is intended for events that should be on every CPU, which does not make sense for uncore events because uncore events do not map one-to-one with CPUs.These 2 requirements are not exactly the same, so introduce a new flag '
requires_cpu' the uncore case.nit: typo missing 'for' the uncore case.
Quoted 1 line
Signed-off-by Adrian Hunter <[email protected]>
Comments coming up in 2 patches time :-)
Thanks,
Ian
Quoted 112 lines
Quoted 28 lines
--- tools/lib/perf/evlist.c | 4 +++- tools/lib/perf/include/internal/evsel.h | 1 + tools/perf/builtin-stat.c | 5 +---- tools/perf/util/evsel.c | 1 + tools/perf/util/parse-events.c | 2 +- 5 files changed, 7 insertions(+), 6 deletions(-)tools/lib/perf/evlist.c +3
-1@@ -43,7 +43,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,if (!evsel->own_cpus || evlist->has_user_cpus) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); - }else if (!evsel->system_wide &&perf_cpu_map__empty (evlist->user_requested_cpus)) { + }else if (!evsel->system_wide && + !evsel->requires_cpu && +perf_cpu_map__empty (evlist->user_requested_cpus)) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); }else if (evsel->cpus != evsel->own_cpus) {tools/lib/perf/include/internal/evsel.h +0
-0tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 51
Quoted 2 lines
tools/lib/perf/include/internal/evsel.h +0
-0@@ -50,6 +50,7 @@ struct perf_evsel {/* parse modifier helper */ int nr_members;From the commit message, could we add the comment:
/* True for events that should be on every CPU. */
However, shouldn't this be captured by the CPU map? Perhaps we can have an invariant check that they agree.
tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 52
Quoted 1 line
tools/lib/perf/include/internal/evsel.h +0
-0bool system_wide;/* True for events that cannot be the any CPU (-1), for example, uncore events. */
Quoted 19 lines
tools/lib/perf/include/internal/evsel.h +1
-0+bool requires_cpu;int idx; };tools/perf/builtin-stat.c +0
-3@@ -385,9 +385,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_if (!counter->supported)return -ENOENT ; -if (counter->core.system_wide) - nthreads =1 ; -for (thread =0 ; thread < nthreads; thread++) {struct perf_counts_values *count;tools/perf/builtin-stat.c static void setup_system_wide(int forks) · line 2265
Quoted 6 lines
tools/perf/builtin-stat.c +1
-1@@ -2264,7 +2261,7 @@ static void setup_system_wide(int forks)struct evsel *counter;evlist__for_each_entry (evsel_list, counter) { -if (!counter->core.system_wide && +if (!counter->core.requires_cpu &&strcmp (counter->name,"duration_time" )) {Off-topic of the patch: this test is a tool event check, it'd be better to do:
if (!counter->core.requires_cpu &&
counter->tool_event!=PERF_TOOL_NONE)Otherwise changes like:
https://lore.kernel.org/linux-perf-users/[email protected]/Will break the test. I'll make a note to do a round of clean up.
Thanks,
IanQuoted 30 lines
tools/perf/builtin-stat.c +0
-0return ; }tools/perf/util/evsel.c +1
-0@@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->core.threads =perf_thread_map__get (orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; + evsel->core.requires_cpu = orig->core.requires_cpu;if (orig->name) { evsel->name =strdup (orig->name);tools/perf/util/parse-events.c +1
-2@@ -365,7 +365,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->core.cpus = cpus; evsel->core.own_cpus =perf_cpu_map__get (cpus); - evsel->core.system_wide = pmu ? pmu->is_uncore : false; + evsel->core.requires_cpu = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats;if (name) --2.25.1
Adrian Hunter
reviewerPATCH 21/23 libperf evsel: Add comments for booleans
In reply to Adrian HunterAdd comments for 'system_wide' and 'requires_cpu' booleans
--- tools/lib/perf/include/internal/evsel.h | 8 ++++++++ 1 file changed, 8 insertions(+)
tools/lib/perf/include/internal/evsel.h +8 -0
@@ -49,7 +49,15 @@ struct perf_evsel {/* parse modifier helper */ int nr_members; +/* +* system_wide is for events that need to be on every CPU, irrespective +* of user requested CPUs or threads. +*/ bool system_wide; +/* +* Some events, for example uncore events, require a CPU. +* i.e. it cannot be -1 +*/ bool requires_cpu;int idx; };
Signature · 1 line
2.25.1
Ian Rogers
reviewerRe: [PATCH V1 21/23] libperf evsel: Add comments for booleans
Quoted 13 lines · Adrian Hunter
Add comments for '
system_wide' and 'requires_cpu' booleansSigned-off-by Adrian Hunter <[email protected]>--- tools/lib/perf/include/internal/evsel.h | 8 ++++++++ 1 file changed, 8 insertions(+)tools/lib/perf/include/internal/evsel.h +0
-0
tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 54
Quoted 6 lines
tools/lib/perf/include/internal/evsel.h +3
-0@@ -49,7 +49,15 @@ struct perf_evsel {/* parse modifier helper */ int nr_members; +/* +* system_wide is for events that need to be on every CPU, irrespective +* of user requested CPUs or threads.
Will the cpu map agree with this? If not, what is the case for all_cpus computed in propagate maps? Could we add this to comment.
tools/lib/perf/include/internal/evsel.h struct perf_evsel { · line 59
Quoted 5 lines
tools/lib/perf/include/internal/evsel.h +4
-0+*/ bool system_wide; +/* +* Some events, for example uncore events, require a CPU. +* i.e. it cannot be -1
nit: perhaps "cannot be 'any CPU' (-1)."
Thanks,
Ian
Quoted 7 lines
tools/lib/perf/include/internal/evsel.h +1
-1+*/ bool requires_cpu;int idx; }; --2.25.1
Adrian Hunter
reviewerPATCH 22/23 perf tools: Allow system-wide events to keep their own CPUs
In reply to Adrian HunterCurrently, user_requested_cpus supplants system-wide CPUs when the evlist has_user_cpus. Change that so that system-wide events retain their own CPUs and they are added to all_cpus.
--- tools/lib/perf/evlist.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
tools/lib/perf/evlist.c +5 -6
@@ -40,12 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,* We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ -if (!evsel->own_cpus || evlist->has_user_cpus) { -perf_cpu_map__put (evsel->cpus); - evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); - }else if (!evsel->system_wide && - !evsel->requires_cpu && -perf_cpu_map__empty (evlist->user_requested_cpus)) { +if (!evsel->own_cpus || + (!evsel->system_wide && evlist->has_user_cpus) || + (!evsel->system_wide && + !evsel->requires_cpu && +perf_cpu_map__empty (evlist->user_requested_cpus))) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); }else if (evsel->cpus != evsel->own_cpus) {
Signature · 1 line
2.25.1
Re: [PATCH V1 22/23] perf tools: Allow system-wide events to keep their own CPUs
Quoted 6 lines · Adrian Hunter
Currently,
user_requested_cpussupplants system-wide CPUs when the evlisthas_user_cpus. Change that so that system-wide events retain their own CPUs and they are added toall_cpus.Signed-off-by Adrian Hunter <[email protected]>
Note, we should really have a test on:
```
$ perf stat -A -e uncore_imc/cas_count_read/ -a -C 1,19 sleep 1
Performance counter stats for 'system wide':
CPU1 974.34 MiB uncore_imc/cas_count_read/
CPU19 262.50 MiB uncore_imc/cas_count_read/
1.003673356 seconds time elapsed
```ie the user requested CPUs were respected for the uncore events even though their CPU mask was {0,18}.
Thanks,
Ian
Quoted 29 lines
--- tools/lib/perf/evlist.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)tools/lib/perf/evlist.c +5
-7@@ -40,12 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,* We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ -if (!evsel->own_cpus || evlist->has_user_cpus) { -perf_cpu_map__put (evsel->cpus); - evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); - }else if (!evsel->system_wide && - !evsel->requires_cpu && -perf_cpu_map__empty (evlist->user_requested_cpus)) { +if (!evsel->own_cpus || + (!evsel->system_wide && evlist->has_user_cpus) || + (!evsel->system_wide && + !evsel->requires_cpu && +perf_cpu_map__empty (evlist->user_requested_cpus))) {perf_cpu_map__put (evsel->cpus); evsel->cpus =perf_cpu_map__get (evlist->user_requested_cpus); }else if (evsel->cpus != evsel->own_cpus) { --2.25.1
Adrian Hunter
reviewerPATCH 23/23 perf tools: Allow system-wide events to keep their own threads
In reply to Adrian HunterSystem-wide events do not have threads, so do not propagate threads to them.
--- tools/lib/perf/evlist.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
tools/lib/perf/evlist.c +5 -2
@@ -52,8 +52,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, evsel->cpus =perf_cpu_map__get (evsel->own_cpus); } -perf_thread_map__put (evsel->threads); - evsel->threads =perf_thread_map__get (evlist->threads); +if (!evsel->system_wide) { +perf_thread_map__put (evsel->threads); + evsel->threads =perf_thread_map__get (evlist->threads); + } + evlist->all_cpus =perf_cpu_map__merge (evlist->all_cpus, evsel->cpus); }
Signature · 1 line
2.25.1
Re: [PATCH V1 23/23] perf tools: Allow system-wide events to keep their own threads
Quoted 5 lines · Adrian Hunter
System-wide events do not have threads, so do not propagate threads to them.
Signed-off-by Adrian Hunter <[email protected]>
Thanks,
Ian
Quoted 25 lines
--- tools/lib/perf/evlist.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)tools/lib/perf/evlist.c +5
-3@@ -52,8 +52,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, evsel->cpus =perf_cpu_map__get (evsel->own_cpus); } -perf_thread_map__put (evsel->threads); - evsel->threads =perf_thread_map__get (evlist->threads); +if (!evsel->system_wide) { +perf_thread_map__put (evsel->threads); + evsel->threads =perf_thread_map__get (evlist->threads); + } + evlist->all_cpus =perf_cpu_map__merge (evlist->all_cpus, evsel->cpus); } --2.25.1
Ian Rogers
reviewerQuoted 178 lines · Adrian Hunter
Hi
Here are V1 patches to support capturing Intel PT sideband events such as mmap, task, context switch, text poke etc, on every CPU even when tracing selected
user_requested_cpus. That is, when using the perf record -C or
--cpu option.This is needed for:
1. text poke: a text poke on any CPU affects all CPUs
2. tracing user space: a user space process can migrate between CPUs so mmap events that happen on a different CPU can be needed to decode auser_requested_cpusCPU.For example:
Trace on CPU 1:
perf record --kcore -C 1 -e intel_pt// &
Start a task on CPU 0:
taskset
0x1testprog &Migrate it to CPU 1:
taskset -p
0x2<testprog pid>Stop tracing:
kill %1
Prior to these changes there will be errors decoding testprog in userspace because the comm and mmap events for testprog will not have been captured.
There is quite a bit of preparation:
The first patch is a small Intel PT test for system-wide side band. The test fails before the patches are applied, passed afterwards.
perf intel-pt: Add a test for system-wide side band [new in V1]
The next 5 patches stop auxtrace mixing up mmap idx between evlist and evsel. That is going to matter when
evlist->all_cpus!=evlist->user_requested_cpus!=evsel->cpus:libperf evsel: Factor out
perf_evsel__ioctl()[now applied] libperf evsel: Addperf_evsel__enable_thread()
perf evlist: Use libperf functions inevlist__enable_event_idx()perf auxtrace: Moveevlist__enable_event_idx()toauxtrace.cperf auxtrace: Do not mix up mmap idxThe next 6 patches stop attempts to auxtrace mmap when it is not an auxtrace event e.g. when mmapping the CPUs on which only sideband is captured:
libperf evlist: Remove ->idx()
per_cpuparameter
libperf evlist: Move ->idx() intommap_per_evsel()
libperf evlist: Add evsel as a parameter to ->idx()
perf auxtrace: Record whether an auxtrace mmap is needed perf auxctrace: Addmmap_neededtoauxtrace_mmap_paramsperf auxtrace: Removeauxtrace_mmap_params__set_idx()per_cpuparameterThe next 5 patches switch to setting up dummy event maps before adding the evsel so that the evsel is subject to map propagation, primarily to cause addition of the evsel's CPUs to
all_cpus.perf evlist: Factor out
evlist__dummy_event()
perf evlist: Addevlist__add_system_wide_dummy()
perf record: Useevlist__add_system_wide_dummy()inrecord__config_text_poke()perf intel-pt: Useevlist__add_system_wide_dummy()for switch tracking perf intel-pt: Track sideband system-wide when neededThe remaining patches make more significant changes.
First change from using
user_requested_cpusto usingall_cpuswhere necessary:perf tools: Allow
all_cpusto be a superset ofuser_requested_cpusSecondly, mmap all per-thread and all per-cpu events:
libperf evlist: Allow mixing per-thread and per-cpu mmaps libperf evlist: Check
nr_mmapsis correct [new in V1]Stop using
system_wideflag for uncore because it will not work anymore:perf stat: Add
requires_cpuflag for uncore libperf evsel: Add comments for booleans [new in V1]Finally change map propagation so that system-wide events retain their cpus and (dummy) threads:
perf tools: Allow system-wide events to keep their own CPUs perf tools: Allow system-wide events to keep their own threads
Changes in V1:
perf intel-pt: Add a test for system-wide side band
New patchlibperf evsel: Factor out
perf_evsel__ioctl()
Dropped because it has been applied.libperf evsel: Add
perf_evsel__enable_thread()
Rename variable i -> idxperf auxtrace: Do not mix up mmap idx
Rename variable cpu tocpu_map_idxperf tools: Allow
all_cpusto be a superset ofuser_requested_cpus
Add Acked-by: Ian Rogers <[email protected]>libperf evlist: Allow mixing per-thread and per-cpu mmaps
Fixperf_evlist__nr_mmaps()calculationlibperf evlist: Check
nr_mmapsis correct
New patchlibperf evsel: Add comments for booleans
New patchperf tools: Allow system-wide events to keep their own CPUs perf tools: Allow system-wide events to keep their own threads
Adrian Hunter (23):
perf intel-pt: Add a test for system-wide side band
libperf evsel: Addperf_evsel__enable_thread()
perf evlist: Use libperf functions inevlist__enable_event_idx()perf auxtrace: Moveevlist__enable_event_idx()toauxtrace.cperf auxtrace: Do not mix up mmap idx
libperf evlist: Remove ->idx()per_cpuparameter
libperf evlist: Move ->idx() intommap_per_evsel()
libperf evlist: Add evsel as a parameter to ->idx()
perf auxtrace: Record whether an auxtrace mmap is needed
perf auxtrace: Addmmap_neededtoauxtrace_mmap_params
perf auxtrace: Removeauxtrace_mmap_params__set_idx()per_cpuparameter perf evlist: Factor outevlist__dummy_event()
perf evlist: Addevlist__add_system_wide_dummy()
perf record: Useevlist__add_system_wide_dummy()inrecord__config_text_poke()perf intel-pt: Useevlist__add_system_wide_dummy()for switch tracking perf intel-pt: Track sideband system-wide when needed
perf tools: Allowall_cpusto be a superset ofuser_requested_cpuslibperf evlist: Allow mixing per-thread and per-cpu mmaps libperf evlist: Checknr_mmapsis correct
perf stat: Addrequires_cpuflag for uncore
libperf evsel: Add comments for booleans
perf tools: Allow system-wide events to keep their own CPUs
perf tools: Allow system-wide events to keep their own threadstools/lib/perf/evlist.c | 80 ++++++++++------------- tools/lib/perf/evsel.c | 10 +++ tools/lib/perf/include/internal/evlist.h | 3 +- tools/lib/perf/include/internal/evsel.h | 9 +++ tools/lib/perf/include/internal/mmap.h | 5 ++ tools/lib/perf/include/perf/evsel.h | 1 + tools/perf/arch/arm/util/cs-etm.c | 1 + tools/perf/arch/arm64/util/arm-spe.c | 1 + tools/perf/arch/s390/util/auxtrace.c | 1 + tools/perf/arch/x86/util/intel-bts.c | 1 + tools/perf/arch/x86/util/intel-pt.c | 32 ++++------ tools/perf/builtin-record.c | 39 +++++------- tools/perf/builtin-stat.c | 5 +- tools/perf/tests/shell/test_intel_pt.sh | 71 +++++++++++++++++++++ tools/perf/util/auxtrace.c | 31 +++++++-- tools/perf/util/auxtrace.h | 8 ++- tools/perf/util/evlist.c | 106 +++++++++++++++---------------- tools/perf/util/evlist.h | 7 +- tools/perf/util/evsel.c | 1 + tools/perf/util/evsel.h | 1 + tools/perf/util/mmap.c | 4 +- tools/perf/util/parse-events.c | 2 +- 22 files changed, 259 insertions(+), 160 deletions(-) create mode 100755 tools/perf/tests/shell/test_intel_pt.sh
Quoted 2 lines
Regards
Adrian
Thanks Adrian, other than a minor build breakage, and some possible function name and comment tweaks, I'm happy with the change. I did 'perf test' on my SkylakeX and things look good too. One last minor thing is the test_intel_pt.sh doesn't test --per-thread mode, this might be good to cover for CPU map propagation issues.
Thanks,
Ian