perf tools: Do not set attr.exclude_guest by default (v4)
Namhyung Kim
maintainercover perf tools: Do not set attr.exclude_guest by default (v4)
Hello,
I found perf tools set exclude_guest bit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.
Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the exclude_guest due to the missing feature detection logic.
v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separate exclude_hv fallback
* rename to exclude_GH_default (Kan)
* drop the RFC from the subject
v3) https://lore.kernel.org/lkml/[email protected]/
* move exclude_guest fallback to the front
* fix precise_max handling on AMD
* simplify the default event for perf record
v2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separate exclude_hv fallback
* add new fallback for exclude_guest
v1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the exclude_guest during the fallback logic.
Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
The code is available at 'perf/exclude-v4' branch ingit://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git
Thanks,
Namhyung
Namhyung Kim (8):
perf tools: Add fallback for exclude_guest perf tools: Don't set attr.exclude_guest by default perf tools: Simplify evsel__add_modifier() perf tools: Do not set exclude_guest for precise_ip perf tools: Detect missing kernel features properly perf tools: Move x86__is_amd_cpu() to util/env.c perf tools: Check fallback error and order perf record: Just use "cycles:P" as the default event
tools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-) delete mode 100644 tools/perf/arch/x86/util/env.c delete mode 100644 tools/perf/arch/x86/util/env.h
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerPATCH 1/8 perf tools: Add fallback for exclude_guest
Commit 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default") changed to parse "cycles:P" event instead of creating a new cycles event for perf record. But it also changed the way how modifiers are handled so it doesn't set the exclude_guest bit by default.
It seems Apple M1 PMU requires exclude_guest set and returns EOPNOTSUPP if not. Let's add a fallback so that it can work with default events.
--- tools/perf/builtin-stat.c | 18 +++++++++++++++--- tools/perf/util/evsel.c | 21 +++++++++++++++++++++ 2 files changed, 36 insertions(+), 3 deletions(-)
tools/perf/builtin-stat.c +15 -3
@@ -639,8 +639,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)* (behavior changed with commit b0a873e). */ if (errno ==EINVAL || errno ==ENOSYS || - errno ==ENOENT || errno ==EOPNOTSUPP || - errno ==ENXIO ) { + errno ==ENOENT || errno ==ENXIO ) {if (verbose >0 )ui__warning ("%s event is not supported by the kernel.\n" ,evsel__name (counter));
@@ -658,7 +657,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)if (verbose >0 )ui__warning ("%s\n" , msg);return COUNTER_RETRY ; - }else if (target__has_per_thread (&target) && + }else if (target__has_per_thread (&target) && errno !=EOPNOTSUPP && evsel_list->core.threads && evsel_list->core.threads->err_thread !=-1 ) {/*
@@ -679,6 +678,19 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)return COUNTER_SKIP ; } +if (errno ==EOPNOTSUPP ) { +if (verbose >0 ) { +ui__warning ("%s event is not supported by the kernel.\n" , +evsel__name (counter)); + } + counter->supported = false; + counter->errored = true; + +if ((evsel__leader (counter) != counter) || + !(counter->core.leader->nr_members >1 )) +return COUNTER_SKIP ; + } +evsel__open_strerror (counter, &target, errno, msg,sizeof (msg));ui__error ("%s\n" , msg);
tools/perf/util/evsel.c +21 -0
@@ -3259,6 +3259,27 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, evsel->core.attr.exclude_kernel =1 ; evsel->core.attr.exclude_hv =1 ; +return true; + }else if (err ==EOPNOTSUPP && !evsel->core.attr.exclude_guest && + !evsel->exclude_GH) { +const char *name =evsel__name (evsel); +char *new_name; +const char *sep =":" ; + +/* Is there already the separator in the name. */ +if (strchr (name,'/' ) || + (strchr (name,':' ) && !evsel->is_libpfm_event)) + sep ="" ; + +if (asprintf (&new_name,"%s%sH" , name, sep) <0 ) +return false; + +free (evsel->name); + evsel->name = new_name; +/* Apple M1 requires exclude_guest */ +scnprintf (msg, msgsize,"trying to fall back to excluding guest samples" ); + evsel->core.attr.exclude_guest =1 ; +return true; }
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 1/8] perf tools: Add fallback for exclude_guest
Quoted 6 lines · Namhyung Kim
Commit
7b100989b4f6bce70("perf evlist: Remove__evlist__add_default") changed to parse "cycles:P" event instead of creating a new cycles event for perf record. But it also changed the way how modifiers are handled so it doesn't set theexclude_guestbit by default.
Quoted 7 lines
It seems Apple M1 PMU requires
exclude_guestset and returns EOPNOTSUPP if not. Let's add a fallback so that it can work with default events.Fixes 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default")Cc Mark Rutland <[email protected]>Cc James Clark <[email protected]>Signed-off-by Namhyung Kim <[email protected]>
Thanks,
Ian
Quoted 83 lines
--- tools/perf/builtin-stat.c | 18 +++++++++++++++--- tools/perf/util/evsel.c | 21 +++++++++++++++++++++ 2 files changed, 36 insertions(+), 3 deletions(-)tools/perf/builtin-stat.c +15
-3@@ -639,8 +639,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)* (behavior changed with commit b0a873e). */ if (errno ==EINVAL || errno ==ENOSYS || - errno ==ENOENT || errno ==EOPNOTSUPP || - errno ==ENXIO ) { + errno ==ENOENT || errno ==ENXIO ) {if (verbose >0 )ui__warning ("%s event is not supported by the kernel.\n" ,evsel__name (counter));@@ -658,7 +657,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)if (verbose >0 )ui__warning ("%s\n" , msg);return COUNTER_RETRY ; - }else if (target__has_per_thread (&target) && + }else if (target__has_per_thread (&target) && errno !=EOPNOTSUPP && evsel_list->core.threads && evsel_list->core.threads->err_thread !=-1 ) {/* @@ -679,6 +678,19 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)return COUNTER_SKIP ; } +if (errno ==EOPNOTSUPP ) { +if (verbose >0 ) { +ui__warning ("%s event is not supported by the kernel.\n" , +evsel__name (counter)); + } + counter->supported = false; + counter->errored = true; + +if ((evsel__leader (counter) != counter) || + !(counter->core.leader->nr_members >1 )) +return COUNTER_SKIP ; + } +evsel__open_strerror (counter, &target, errno, msg,sizeof (msg));ui__error ("%s\n" , msg);tools/perf/util/evsel.c +21
-1@@ -3259,6 +3259,27 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, evsel->core.attr.exclude_kernel =1 ; evsel->core.attr.exclude_hv =1 ; +return true; + }else if (err ==EOPNOTSUPP && !evsel->core.attr.exclude_guest && + !evsel->exclude_GH) { +const char *name =evsel__name (evsel); +char *new_name; +const char *sep =":" ; + +/* Is there already the separator in the name. */ +if (strchr (name,'/' ) || + (strchr (name,':' ) && !evsel->is_libpfm_event)) + sep ="" ; + +if (asprintf (&new_name,"%s%sH" , name, sep) <0 ) +return false; + +free (evsel->name); + evsel->name = new_name; +/* Apple M1 requires exclude_guest */ +scnprintf (msg, msgsize,"trying to fall back to excluding guest samples" ); + evsel->core.attr.exclude_guest =1 ; +return true; } --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerPATCH 2/8 perf tools: Don't set attr.exclude_guest by default
In reply to Namhyung KimThe exclude_guest in the event attribute is to limit profiling in the host environment. But I'm not sure why we want to set it by default cause we don't care about it in most cases and I feel like it just makes new PMU implementation complicated.
Of course it's useful for perf kvm command so I added the exclude_GH_default variable to preserve the old behavior for perf kvm and other commands like perf record and stat won't set the exclude bit. This is helpful for AMD IBS case since having exclude_guest bit will clear new feature bit due to the missing feature check logic.
$ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 0
$ perf record -W -e ibs_op// -vv true 2>&1 | grep switching switching off PERF_FORMAT_LOST support switching off weight struct support switching off bpf_event switching off ksymbol switching off cloexec flag switching off mmap2 switching off exclude_guest, exclude_host
Intestingly, I found it sets the exclude_bit if "u" modifier is used. I don't know why but it's neither intuitive nor consistent. Let's remove the bit there too.
--- tools/perf/builtin-kvm.c | 1 + tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 18 +++++++++--------- tools/perf/util/parse-events.c | 2 +- tools/perf/util/util.c | 10 ++++++++-- tools/perf/util/util.h | 3 +++ 6 files changed, 23 insertions(+), 13 deletions(-)
tools/perf/builtin-kvm.c +1 -0
@@ -2147,6 +2147,7 @@ int cmd_kvm(int argc, const char **argv) "buildid-list", "stat", NULL };const char *kvm_usage[] = {NULL ,NULL }; + exclude_GH_default = true; perf_host =0 ; perf_guest =1 ;
tools/perf/tests/attr/test-record-dummy-C0 +1 -1
@@ -37,7 +37,7 @@ precise_ip=0 mmap_data=0 sample_id_all=1 exclude_host=0 -exclude_guest=1 +exclude_guest=0 exclude_callchain_kernel=0 exclude_callchain_user=0 mmap2=1
tools/perf/tests/parse-events.c +9 -9
@@ -932,7 +932,7 @@ static int test__group2(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));
@@ -947,7 +947,7 @@ static int test__group2(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);if (evsel__has_leader (evsel, leader))
@@ -1072,7 +1072,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));
@@ -1222,7 +1222,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));
@@ -1437,7 +1437,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);
@@ -1453,7 +1453,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));
@@ -1468,7 +1468,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);
@@ -1497,7 +1497,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);
@@ -1513,7 +1513,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);
tools/perf/util/parse-events.c +1 -1
@@ -1776,7 +1776,7 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,if (mod.user) {if (!exclude) exclude = eu = ek = eh =1 ; -if (!exclude_GH && !perf_guest) +if (!exclude_GH && !perf_guest && exclude_GH_default) eG =1 ; eu =0 ; }
tools/perf/util/util.c +8 -2
@@ -78,17 +78,23 @@ bool sysctl__nmi_watchdog_enabled(void)bool test_attr__enabled; +bool exclude_GH_default; +bool perf_host = true;bool perf_guest = false;void event_attr_init (struct perf_event_attr *attr) { +/* to capture ABI version */ + attr->size =sizeof (*attr); + +if (!exclude_GH_default) +return ; +if (!perf_host) attr->exclude_host =1 ;if (!perf_guest) attr->exclude_guest =1 ; -/* to capture ABI version */ - attr->size =sizeof (*attr); }int mkdir_p (char *path,mode_t mode)
tools/perf/util/util.h +3 -0
@@ -21,6 +21,9 @@ extern const char perf_more_info_string[];extern const char *input_name; +/* This will control if perf_{host,guest} will set attr.exclude_{host,guest}. */ +extern bool exclude_GH_default; +extern bool perf_host;extern bool perf_guest;
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 2/8] perf tools: Don't set attr.exclude_guest by default
Quoted 24 lines · Namhyung Kim
The
exclude_guestin the event attribute is to limit profiling in the host environment. But I'm not sure why we want to set it by default cause we don't care about it in most cases and I feel like it just makes new PMU implementation complicated.Of course it's useful for perf kvm command so I added the
exclude_GH_defaultvariable to preserve the old behavior for perf kvm and other commands like perf record and stat won't set the exclude bit. This is helpful for AMD IBS case since havingexclude_guestbit will clear new feature bit due to the missing feature check logic.$ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 0$ perf record -W -e ibs_op// -vv true 2>&1 | grep switching switching off PERF_FORMAT_LOST support switching off weight struct support switching off bpf_event switching off ksymbol switching off cloexec flag switching off mmap2 switching off exclude_guest, exclude_host
Quoted 8 lines
Intestingly, I found it sets the
exclude_bitif "u" modifier is used. I don't know why but it's neither intuitive nor consistent. Let's remove the bit there too.Cc Mark Rutland <[email protected]>Cc James Clark <[email protected]>Cc Ravi Bangoria <[email protected]>Signed-off-by Namhyung Kim <[email protected]>
Thanks,
Ian
Quoted 179 lines
--- tools/perf/builtin-kvm.c | 1 + tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 18 +++++++++--------- tools/perf/util/parse-events.c | 2 +- tools/perf/util/util.c | 10 ++++++++-- tools/perf/util/util.h | 3 +++ 6 files changed, 23 insertions(+), 13 deletions(-)tools/perf/builtin-kvm.c +1
-0@@ -2147,6 +2147,7 @@ int cmd_kvm(int argc, const char **argv) "buildid-list", "stat", NULL };const char *kvm_usage[] = {NULL ,NULL }; + exclude_GH_default = true; perf_host =0 ; perf_guest =1 ;tools/perf/tests/attr/test-record-dummy-C0 +1
-1@@ -37,7 +37,7 @@ precise_ip=0 mmap_data=0 sample_id_all=1 exclude_host=0 -exclude_guest=1 +exclude_guest=0 exclude_callchain_kernel=0 exclude_callchain_user=0 mmap2=1tools/perf/tests/parse-events.c +9
-9@@ -932,7 +932,7 @@ static int test__group2(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));@@ -947,7 +947,7 @@ static int test__group2(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);if (evsel__has_leader (evsel, leader))@@ -1072,7 +1072,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));@@ -1222,7 +1222,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel));@@ -1437,7 +1437,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);@@ -1453,7 +1453,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));@@ -1468,7 +1468,7 @@ static int test__leader_sample1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);@@ -1497,7 +1497,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);@@ -1513,7 +1513,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->core.attr.precise_ip);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);tools/perf/util/parse-events.c +1
-1@@ -1776,7 +1776,7 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,if (mod.user) {if (!exclude) exclude = eu = ek = eh =1 ; -if (!exclude_GH && !perf_guest) +if (!exclude_GH && !perf_guest && exclude_GH_default) eG =1 ; eu =0 ; }tools/perf/util/util.c +8
-2@@ -78,17 +78,23 @@ bool sysctl__nmi_watchdog_enabled(void)bool test_attr__enabled; +bool exclude_GH_default; +bool perf_host = true;bool perf_guest = false;void event_attr_init (struct perf_event_attr *attr) { +/* to capture ABI version */ + attr->size =sizeof (*attr); + +if (!exclude_GH_default) +return ; +if (!perf_host) attr->exclude_host =1 ;if (!perf_guest) attr->exclude_guest =1 ; -/* to capture ABI version */ - attr->size =sizeof (*attr); }int mkdir_p (char *path,mode_t mode)tools/perf/util/util.h +3
-1@@ -21,6 +21,9 @@ extern const char perf_more_info_string[];extern const char *input_name; +/* This will control if perf_{host,guest} will set attr.exclude_{host,guest}. */ +extern bool exclude_GH_default; +extern bool perf_host;extern bool perf_guest; --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerPATCH 3/8 perf tools: Simplify evsel__add_modifier()
In reply to Namhyung KimSince it doesn't set the exclude_guest, no need to special handle the bit and simply show only if one of host or guest bit is set. Now the default event name might not have :H prefix anymore so change the dlfilter test not to compare the ":" at the end.
--- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/util/evsel.c | 5 +---- 3 files changed, 3 insertions(+), 6 deletions(-)
tools/perf/dlfilters/dlfilter-test-api-v0.c +1 -1
@@ -220,7 +220,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sampleCHECK_SAMPLE (raw_callchain_nr);CHECK (!sample->raw_callchain); -#define EVENT_NAME "branches:" +#define EVENT_NAME "branches"CHECK (!strncmp (sample->event,EVENT_NAME ,strlen (EVENT_NAME )));return 0 ;
tools/perf/dlfilters/dlfilter-test-api-v2.c +1 -1
@@ -235,7 +235,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sampleCHECK_SAMPLE (raw_callchain_nr);CHECK (!sample->raw_callchain); -#define EVENT_NAME "branches:" +#define EVENT_NAME "branches"CHECK (!strncmp (sample->event,EVENT_NAME ,strlen (EVENT_NAME )));return 0 ;
tools/perf/util/evsel.c +1 -4
@@ -545,7 +545,6 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) {int colon =0 , r =0 ;struct perf_event_attr *attr = &evsel->core.attr; -bool exclude_guest_default = false;#define MOD_PRINT (context, mod) do { \ if (!attr->exclude_##context) { \
@@ -557,17 +556,15 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)MOD_PRINT (kernel,'k' );MOD_PRINT (user,'u' );MOD_PRINT (hv,'h' ); - exclude_guest_default = true; }if (attr->precise_ip) {if (!colon) colon = ++r; r +=scnprintf (bf + r, size - r,"%.*s" , attr->precise_ip,"ppp" ); - exclude_guest_default = true; } -if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) { +if (attr->exclude_host || attr->exclude_guest) {MOD_PRINT (host,'H' );MOD_PRINT (guest,'G' ); }
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 3/8] perf tools: Simplify evsel__add_modifier()
Quoted 7 lines · Namhyung Kim
Since it doesn't set the
exclude_guest, no need to special handle the bit and simply show only if one of host or guest bit is set. Now the default event name might not have :H prefix anymore so change the dlfilter test not to compare the ":" at the end.Signed-off-by Namhyung Kim <[email protected]>
Thanks,
Ian
Quoted 66 lines
--- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/util/evsel.c | 5 +---- 3 files changed, 3 insertions(+), 6 deletions(-)tools/perf/dlfilters/dlfilter-test-api-v0.c +1
-1@@ -220,7 +220,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sampleCHECK_SAMPLE (raw_callchain_nr);CHECK (!sample->raw_callchain); -#define EVENT_NAME "branches:" +#define EVENT_NAME "branches"CHECK (!strncmp (sample->event,EVENT_NAME ,strlen (EVENT_NAME )));return 0 ;tools/perf/dlfilters/dlfilter-test-api-v2.c +1
-1@@ -235,7 +235,7 @@ static int check_sample(struct filter_data *d, const struct perf_dlfilter_sampleCHECK_SAMPLE (raw_callchain_nr);CHECK (!sample->raw_callchain); -#define EVENT_NAME "branches:" +#define EVENT_NAME "branches"CHECK (!strncmp (sample->event,EVENT_NAME ,strlen (EVENT_NAME )));return 0 ;tools/perf/util/evsel.c +1
-5@@ -545,7 +545,6 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) {int colon =0 , r =0 ;struct perf_event_attr *attr = &evsel->core.attr; -bool exclude_guest_default = false;#define MOD_PRINT (context, mod) do { \ if (!attr->exclude_##context) { \@@ -557,17 +556,15 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)MOD_PRINT (kernel,'k' );MOD_PRINT (user,'u' );MOD_PRINT (hv,'h' ); - exclude_guest_default = true; }if (attr->precise_ip) {if (!colon) colon = ++r; r +=scnprintf (bf + r, size - r,"%.*s" , attr->precise_ip,"ppp" ); - exclude_guest_default = true; } -if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) { +if (attr->exclude_host || attr->exclude_guest) {MOD_PRINT (host,'H' );MOD_PRINT (guest,'G' ); } --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerPATCH 4/8 perf tools: Do not set exclude_guest for precise_ip
In reply to Namhyung KimIt seems perf sets the exclude_guest bit because of Intel PEBS implementation which uses a virtual address. IIUC now kernel disables PEBS when it goes to the guest mode regardless of this bit so we don't need to set it explicitly. At least for the other archs/vendors.
I found the commit 1342798cc13e set the exclude_guest for precise_ip in the tool and the commit 20b279ddb38c added kernel side enforcement which was reverted by commit a706d965dcfd later.
Actually it doesn't set the exclude_guest for the default event (cycles:P) already.
$ grep -m1 vendor /proc/cpuinfo vendor_id : GenuineIntel
$ perf record -e cycles:P true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]
$ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise precise_ip: 3
But having lower 'p' modifier set the bit for some reason.
$ perf record -e cycles:pp true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]
$ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise precise_ip: 2 exclude_guest: 1
Actually AMD IBS suffers from this because it doesn't support excludes and having this bit effectively disables new features in the current implementation (due to the missing feature check).
$ grep -m1 vendor /proc/cpuinfo vendor_id : AuthenticAMD
$ perf record -W -e cycles:p -vv true 2>&1 | grep switching switching off PERF_FORMAT_LOST support switching off weight struct support switching off bpf_event switching off ksymbol switching off cloexec flag switching off mmap2 switching off exclude_guest, exclude_host
By not setting exclude_guest, we can fix this inconsistency and the troubles.
--- tools/perf/tests/parse-events.c | 12 ++++-------- tools/perf/util/parse-events.c | 4 ---- 2 files changed, 4 insertions(+), 12 deletions(-)
tools/perf/tests/parse-events.c +4 -8
@@ -898,8 +898,7 @@ static int test__group1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));
@@ -1016,9 +1015,8 @@ static int test__group3(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ TEST_ASSERT_VAL ("wrong exclude guest" , - evsel->core.attr.exclude_guest); + !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip",
@@ -1103,8 +1101,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==1 );TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);
@@ -1122,8 +1119,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));
tools/perf/util/parse-events.c +0 -4
@@ -1769,10 +1769,6 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,int exclude = eu | ek | eh;int exclude_GH = group ? evsel->exclude_GH :0 ; -if (mod.precise) { -/* use of precise requires exclude_guest */ - eG =1 ; - }if (mod.user) {if (!exclude) exclude = eu = ek = eh =1 ;
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 4/8] perf tools: Do not set exclude_guest for precise_ip
Quoted 49 lines · Namhyung Kim
It seems perf sets the
exclude_guestbit because of Intel PEBS implementation which uses a virtual address. IIUC now kernel disables PEBS when it goes to the guest mode regardless of this bit so we don't need to set it explicitly. At least for the other archs/vendors.I found the commit
1342798cc13eset theexclude_guestforprecise_ipin the tool and the commit20b279ddb38cadded kernel side enforcement which was reverted by commita706d965dcfdlater.Actually it doesn't set the
exclude_guestfor the default event (cycles:P) already.$ grep -m1 vendor /proc/cpuinfo vendor_id : GenuineIntel$ perf record -e cycles:P true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]$ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise precise_ip: 3But having lower 'p' modifier set the bit for some reason.
$ perf record -e cycles:pp true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (9 samples) ]$ perf evlist -v | tr ',' '\n' | grep -e exclude -e precise precise_ip: 2 exclude_guest: 1Actually AMD IBS suffers from this because it doesn't support excludes and having this bit effectively disables new features in the current implementation (due to the missing feature check).
$ grep -m1 vendor /proc/cpuinfo vendor_id : AuthenticAMD$ perf record -W -e cycles:p -vv true 2>&1 | grep switching switching off PERF_FORMAT_LOST support switching off weight struct support switching off bpf_event switching off ksymbol switching off cloexec flag switching off mmap2 switching off exclude_guest, exclude_host
Quoted 4 lines
By not setting
exclude_guest, we can fix this inconsistency and the troubles.Signed-off-by Namhyung Kim <[email protected]>
Thanks,
Ian
Quoted 68 lines
--- tools/perf/tests/parse-events.c | 12 ++++-------- tools/perf/util/parse-events.c | 4 ---- 2 files changed, 4 insertions(+), 12 deletions(-)tools/perf/tests/parse-events.c +4
-8@@ -898,8 +898,7 @@ static int test__group1(struct evlist *evlist)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));@@ -1016,9 +1015,8 @@ static int test__group3(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ TEST_ASSERT_VAL ("wrong exclude guest" , - evsel->core.attr.exclude_guest); + !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip",@@ -1103,8 +1101,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==1 );TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);@@ -1122,8 +1119,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude_user" , evsel->core.attr.exclude_user);TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->core.attr.exclude_kernel);TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->core.attr.exclude_hv); -/* use of precise requires exclude_guest */ -TEST_ASSERT_VAL ("wrong exclude guest" , evsel->core.attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude guest" , !evsel->core.attr.exclude_guest);TEST_ASSERT_VAL ("wrong exclude host" , !evsel->core.attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , evsel->core.attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" ,evsel__has_leader (evsel, leader));tools/perf/util/parse-events.c +0
-5@@ -1769,10 +1769,6 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,int exclude = eu | ek | eh;int exclude_GH = group ? evsel->exclude_GH :0 ; -if (mod.precise) { -/* use of precise requires exclude_guest */ - eG =1 ; - }if (mod.user) {if (!exclude) exclude = eu = ek = eh =1 ; --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerPATCH 5/8 perf tools: Detect missing kernel features properly
In reply to Namhyung KimThe evsel__detect_missing_features() is to check if the attributes of the evsel is supported or not. But it checks the attribute based on the given evsel, it might miss something if the attr doesn't have the bit or give incorrect results if the event is special.
Also it maintains the order of the feature that was added to the kernel which means it can assume older features should be supported once it detects the current feature is working. To minimized the confusion and to accurately check the kernel features, I think it's better to use a software event and go through all the features at once.
Also make the function static since it's only used in evsel.c.
--- tools/perf/util/evsel.c | 345 +++++++++++++++++++++++++++++----------- tools/perf/util/evsel.h | 1 - 2 files changed, 249 insertions(+), 97 deletions(-)
tools/perf/util/evsel.c +249 -96
@@ -20,6 +20,7 @@#include <linux/zalloc.h> #include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/syscall.h> #include <sys/types.h> #include <dirent.h> #include <stdlib.h>
@@ -2150,120 +2151,272 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,return err; } -bool evsel__detect_missing_features (struct evsel *evsel) +static bool has_attr_feature (struct perf_event_attr *attr,unsigned long flags) { +int fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + +if (fd <0 ) { + attr->exclude_kernel =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_hv =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_guest =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + + attr->exclude_kernel =0 ; + attr->exclude_guest =0 ; + attr->exclude_hv =0 ; + +return fd >=0 ; +} + +static void evsel__detect_missing_brstack_features (struct evsel *evsel) +{ +static bool detection_done = false; +struct perf_event_attr attr = { + .type = evsel->core.attr.type, + .config = evsel->core.attr.config, + .disabled =1 , + .sample_type =PERF_SAMPLE_BRANCH_STACK , + .sample_period =1000 , + }; +int old_errno; + +if (detection_done) +return ; + + old_errno = errno; +/* * Must probe features in the order they were added to the -* perf_event_attr interface. +* perf_event_attr interface. These are PMU specific limitation +* so we can detect with the given hardware event and stop on the +* first one succeeded. */ -if (!perf_missing_features.branch_counters && - (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_COUNTERS )) { - perf_missing_features.branch_counters = true; -pr_debug2 ("switching off branch counters support\n" ); -return true; - }else if (!perf_missing_features.read_lost && - (evsel->core.attr.read_format &PERF_FORMAT_LOST )) { - perf_missing_features.read_lost = true; -pr_debug2 ("switching off PERF_FORMAT_LOST support\n" ); + +/* Please add new feature detection here. */ + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_COUNTERS ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.branch_counters = true; +pr_debug2 ("switching off branch counters support\n" ); + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_HW_INDEX ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.branch_hw_idx = true; +pr_debug2 ("switching off branch HW index support\n" ); + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_NO_CYCLES |PERF_SAMPLE_BRANCH_NO_FLAGS ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.lbr_flags = true; +pr_debug2_peo ("switching off branch sample type no (cycles/flags)\n" ); + +found: + detection_done = true; + errno = old_errno; +} + +static bool evsel__detect_missing_features (struct evsel *evsel) +{ +static bool detection_done = false; +struct perf_event_attr attr = { + .type =PERF_TYPE_SOFTWARE , + .config =PERF_COUNT_SW_TASK_CLOCK , + .disabled =1 , + }; +int old_errno; + +if (evsel__has_br_stack (evsel)) +evsel__detect_missing_brstack_features (evsel); + +if (detection_done) + goto check; + + old_errno = errno; + +/* +* Must probe features in the order they were added to the +* perf_event_attr interface. These are kernel core limitation +* not PMU-specific so we can detect with a software event and +* stop on the first one succeeded. +*/ + +/* Please add new feature detection here. */ + + attr.read_format =PERF_FORMAT_LOST ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.read_lost = true; +pr_debug2 ("switching off PERF_FORMAT_LOST support\n" ); + attr.read_format =0 ; + + attr.sample_type =PERF_SAMPLE_WEIGHT_STRUCT ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.weight_struct = true; +pr_debug2 ("switching off weight struct support\n" ); + attr.sample_type =0 ; + + attr.sample_type =PERF_SAMPLE_CODE_PAGE_SIZE ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.code_page_size = true; +pr_debug2_peo ("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support\n" ); + attr.sample_type =0 ; + + attr.sample_type =PERF_SAMPLE_DATA_PAGE_SIZE ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.data_page_size = true; +pr_debug2_peo ("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support\n" ); + attr.sample_type =0 ; + + attr.cgroup =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.cgroup = true; +pr_debug2_peo ("Kernel has no cgroup sampling support\n" ); + attr.cgroup =0 ; + + attr.aux_output =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.aux_output = true; +pr_debug2_peo ("Kernel has no attr.aux_output support\n" ); + attr.aux_output =0 ; + + attr.bpf_event =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.bpf = true; +pr_debug2_peo ("switching off bpf_event\n" ); + attr.bpf_event =0 ; + + attr.ksymbol =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.ksymbol = true; +pr_debug2_peo ("switching off ksymbol\n" ); + attr.ksymbol =0 ; + + attr.write_backward =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.write_backward = true; +pr_debug2_peo ("switching off write_backward\n" ); + attr.write_backward =0 ; + + attr.use_clockid =1 ; + attr.clockid =CLOCK_MONOTONIC ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.clockid = true; +pr_debug2_peo ("switching off clockid\n" ); + attr.use_clockid =0 ; + attr.clockid =0 ; + +if (has_attr_feature (&attr,/*flags=*/ PERF_FLAG_FD_CLOEXEC )) + goto found; + perf_missing_features.cloexec = true; +pr_debug2_peo ("switching off cloexec flag\n" ); + + attr.mmap2 =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.mmap2 = true; +pr_debug2_peo ("switching off mmap2\n" ); + attr.mmap2 =0 ; + +/* set this unconditionally? */ + perf_missing_features.sample_id_all = true; +pr_debug2_peo ("switching off sample_id_all\n" ); + + attr.inherit =1 ; + attr.read_format =PERF_FORMAT_GROUP ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.group_read = true; +pr_debug2_peo ("switching off group read\n" ); + attr.inherit =0 ; + attr.read_format =0 ; + +found: + detection_done = true; + errno = old_errno; + +check: +if ((evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_COUNTERS ) && + perf_missing_features.branch_counters)return true; - }else if (!perf_missing_features.weight_struct && - (evsel->core.attr.sample_type &PERF_SAMPLE_WEIGHT_STRUCT )) { - perf_missing_features.weight_struct = true; -pr_debug2 ("switching off weight struct support\n" ); + +if ((evsel->core.attr.read_format &PERF_FORMAT_LOST ) && + perf_missing_features.read_lost)return true; - }else if (!perf_missing_features.code_page_size && - (evsel->core.attr.sample_type &PERF_SAMPLE_CODE_PAGE_SIZE )) { - perf_missing_features.code_page_size = true; -pr_debug2_peo ("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support, bailing out\n" ); -return false; - }else if (!perf_missing_features.data_page_size && - (evsel->core.attr.sample_type &PERF_SAMPLE_DATA_PAGE_SIZE )) { - perf_missing_features.data_page_size = true; -pr_debug2_peo ("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n" ); -return false; - }else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { - perf_missing_features.cgroup = true; -pr_debug2_peo ("Kernel has no cgroup sampling support, bailing out\n" ); -return false; - }else if (!perf_missing_features.branch_hw_idx && - (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX )) { - perf_missing_features.branch_hw_idx = true; -pr_debug2 ("switching off branch HW index support\n" ); + +if ((evsel->core.attr.sample_type &PERF_SAMPLE_WEIGHT_STRUCT ) && + perf_missing_features.weight_struct)return true; - }else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { - perf_missing_features.aux_output = true; -pr_debug2_peo ("Kernel has no attr.aux_output support, bailing out\n" ); -return false; - }else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) { - perf_missing_features.bpf = true; -pr_debug2_peo ("switching off bpf_event\n" ); + +if (evsel->core.attr.use_clockid && evsel->core.attr.clockid !=CLOCK_MONOTONIC && + !perf_missing_features.clockid) { + perf_missing_features.clockid_wrong = true;return true; - }else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { - perf_missing_features.ksymbol = true; -pr_debug2_peo ("switching off ksymbol\n" ); + } + +if (evsel->core.attr.use_clockid && perf_missing_features.clockid)return true; - }else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { - perf_missing_features.write_backward = true; -pr_debug2_peo ("switching off write_backward\n" ); -return false; - }else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { - perf_missing_features.clockid_wrong = true; -pr_debug2_peo ("switching off clockid\n" ); + +if ((evsel->open_flags &PERF_FLAG_FD_CLOEXEC ) && + perf_missing_features.cloexec)return true; - }else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { - perf_missing_features.clockid = true; -pr_debug2_peo ("switching off use_clockid\n" ); + +if (evsel->core.attr.mmap2 && perf_missing_features.mmap2)return true; - }else if (!perf_missing_features.cloexec && (evsel->open_flags &PERF_FLAG_FD_CLOEXEC )) { - perf_missing_features.cloexec = true; -pr_debug2_peo ("switching off cloexec flag\n" ); + +if ((evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_FLAGS | +PERF_SAMPLE_BRANCH_NO_CYCLES )) && + perf_missing_features.lbr_flags)return true; - }else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { - perf_missing_features.mmap2 = true; -pr_debug2_peo ("switching off mmap2\n" ); + +if (evsel->core.attr.inherit && (evsel->core.attr.read_format &PERF_FORMAT_GROUP ) && + perf_missing_features.group_read)return true; - }else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) { -if (evsel->pmu ==NULL ) - evsel->pmu =evsel__find_pmu (evsel); - -if (evsel->pmu) - evsel->pmu->missing_features.exclude_guest = true; -else { -/* we cannot find PMU, disable attrs now */ - evsel->core.attr.exclude_host = false; - evsel->core.attr.exclude_guest = false; - } -if (evsel->exclude_GH) { -pr_debug2_peo ("PMU has no exclude_host/guest support, bailing out\n" ); -return false; - } -if (!perf_missing_features.exclude_guest) { - perf_missing_features.exclude_guest = true; -pr_debug2_peo ("switching off exclude_guest, exclude_host\n" ); - } +if (evsel->core.attr.ksymbol && perf_missing_features.ksymbol)return true; - }else if (!perf_missing_features.sample_id_all) { - perf_missing_features.sample_id_all = true; -pr_debug2_peo ("switching off sample_id_all\n" ); + +if (evsel->core.attr.bpf_event && perf_missing_features.bpf)return true; - }else if (!perf_missing_features.lbr_flags && - (evsel->core.attr.branch_sample_type & - (PERF_SAMPLE_BRANCH_NO_CYCLES | -PERF_SAMPLE_BRANCH_NO_FLAGS ))) { - perf_missing_features.lbr_flags = true; -pr_debug2_peo ("switching off branch sample type no (cycles/flags)\n" ); + +if ((evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX ) && + perf_missing_features.branch_hw_idx)return true; - }else if (!perf_missing_features.group_read && - evsel->core.attr.inherit && - (evsel->core.attr.read_format &PERF_FORMAT_GROUP ) && -evsel__is_group_leader (evsel)) { - perf_missing_features.group_read = true; -pr_debug2_peo ("switching off group read\n" ); + +if (evsel->core.attr.sample_id_all && perf_missing_features.sample_id_all)return true; - }else { -return false; - } + +return false; } static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
tools/perf/util/evsel.h +0 -1
@@ -368,7 +368,6 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,void evsel__close (struct evsel *evsel);int evsel__prepare_open (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads); -bool evsel__detect_missing_features (struct evsel *evsel);bool evsel__precise_ip_fallback (struct evsel *evsel);
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Ian Rogers
reviewerRe: [PATCH 5/8] perf tools: Detect missing kernel features properly
Quoted 65 lines · Namhyung Kim
The
evsel__detect_missing_features()is to check if the attributes of the evsel is supported or not. But it checks the attribute based on the given evsel, it might miss something if the attr doesn't have the bit or give incorrect results if the event is special.Also it maintains the order of the feature that was added to the kernel which means it can assume older features should be supported once it detects the current feature is working. To minimized the confusion and to accurately check the kernel features, I think it's better to use a software event and go through all the features at once.
Also make the function static since it's only used in
evsel.c.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 345 +++++++++++++++++++++++++++++----------- tools/perf/util/evsel.h | 1 - 2 files changed, 249 insertions(+), 97 deletions(-)tools/perf/util/evsel.c +28
-1@@ -20,6 +20,7 @@#include <linux/zalloc.h> #include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/syscall.h> #include <sys/types.h> #include <dirent.h> #include <stdlib.h> @@ -2150,120 +2151,272 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,return err; } -bool evsel__detect_missing_features (struct evsel *evsel) +static bool has_attr_feature (struct perf_event_attr *attr,unsigned long flags) { +int fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + +if (fd <0 ) { + attr->exclude_kernel =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_hv =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_guest =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd);
tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2191
Quoted 10 lines
tools/perf/util/evsel.c +10
-0+ } + + attr->exclude_kernel =0 ; + attr->exclude_guest =0 ; + attr->exclude_hv =0 ; + +return fd >=0 ; +} + +static void evsel__detect_missing_brstack_features (struct evsel *evsel)
In the future could other PMU specific unsupported features be added not just brstack? Perhaps evsel__detect_missing_pmu_features would better capture that.
Quoted 29 lines
tools/perf/util/evsel.c +19
-7+{ +static bool detection_done = false; +struct perf_event_attr attr = { + .type = evsel->core.attr.type, + .config = evsel->core.attr.config, + .disabled =1 , + .sample_type =PERF_SAMPLE_BRANCH_STACK , + .sample_period =1000 , + }; +int old_errno; + +if (detection_done) +return ; + + old_errno = errno; +/* * Must probe features in the order they were added to the -* perf_event_attr interface. +* perf_event_attr interface. These are PMU specific limitation +* so we can detect with the given hardware event and stop on the +* first one succeeded. */ -if (!perf_missing_features.branch_counters && - (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_COUNTERS )) { - perf_missing_features.branch_counters = true; -pr_debug2 ("switching off branch counters support\n" ); -return true; - } else if (!perf_missing_features.read_lost &&
tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2220
Quoted 10 lines
tools/perf/util/evsel.c +7
-3- (evsel->core.attr.read_format & PERF_FORMAT_LOST)) { - perf_missing_features.read_lost = true; -pr_debug2 ("switching off PERF_FORMAT_LOST support\n" ); + +/* Please add new feature detection here. */ + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_COUNTERS ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.branch_counters = true;
It feels like these global variables should be part of the PMU state. There is already perf_pmu.missing_features.
Thanks,
Ian
Quoted 302 lines
tools/perf/util/evsel.c +185
-85+pr_debug2 ("switching off branch counters support\n" ); + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_HW_INDEX ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.branch_hw_idx = true; +pr_debug2 ("switching off branch HW index support\n" ); + + attr.branch_sample_type =PERF_SAMPLE_BRANCH_NO_CYCLES |PERF_SAMPLE_BRANCH_NO_FLAGS ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.lbr_flags = true; +pr_debug2_peo ("switching off branch sample type no (cycles/flags)\n" ); + +found: + detection_done = true; + errno = old_errno; +} + +static bool evsel__detect_missing_features (struct evsel *evsel) +{ +static bool detection_done = false; +struct perf_event_attr attr = { + .type =PERF_TYPE_SOFTWARE , + .config =PERF_COUNT_SW_TASK_CLOCK , + .disabled =1 , + }; +int old_errno; + +if (evsel__has_br_stack (evsel)) +evsel__detect_missing_brstack_features (evsel); + +if (detection_done) + goto check; + + old_errno = errno; + +/* +* Must probe features in the order they were added to the +* perf_event_attr interface. These are kernel core limitation +* not PMU-specific so we can detect with a software event and +* stop on the first one succeeded. +*/ + +/* Please add new feature detection here. */ + + attr.read_format =PERF_FORMAT_LOST ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.read_lost = true; +pr_debug2 ("switching off PERF_FORMAT_LOST support\n" ); + attr.read_format =0 ; + + attr.sample_type =PERF_SAMPLE_WEIGHT_STRUCT ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.weight_struct = true; +pr_debug2 ("switching off weight struct support\n" ); + attr.sample_type =0 ; + + attr.sample_type =PERF_SAMPLE_CODE_PAGE_SIZE ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.code_page_size = true; +pr_debug2_peo ("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support\n" ); + attr.sample_type =0 ; + + attr.sample_type =PERF_SAMPLE_DATA_PAGE_SIZE ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.data_page_size = true; +pr_debug2_peo ("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support\n" ); + attr.sample_type =0 ; + + attr.cgroup =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.cgroup = true; +pr_debug2_peo ("Kernel has no cgroup sampling support\n" ); + attr.cgroup =0 ; + + attr.aux_output =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.aux_output = true; +pr_debug2_peo ("Kernel has no attr.aux_output support\n" ); + attr.aux_output =0 ; + + attr.bpf_event =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.bpf = true; +pr_debug2_peo ("switching off bpf_event\n" ); + attr.bpf_event =0 ; + + attr.ksymbol =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.ksymbol = true; +pr_debug2_peo ("switching off ksymbol\n" ); + attr.ksymbol =0 ; + + attr.write_backward =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.write_backward = true; +pr_debug2_peo ("switching off write_backward\n" ); + attr.write_backward =0 ; + + attr.use_clockid =1 ; + attr.clockid =CLOCK_MONOTONIC ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.clockid = true; +pr_debug2_peo ("switching off clockid\n" ); + attr.use_clockid =0 ; + attr.clockid =0 ; + +if (has_attr_feature (&attr,/*flags=*/ PERF_FLAG_FD_CLOEXEC )) + goto found; + perf_missing_features.cloexec = true; +pr_debug2_peo ("switching off cloexec flag\n" ); + + attr.mmap2 =1 ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.mmap2 = true; +pr_debug2_peo ("switching off mmap2\n" ); + attr.mmap2 =0 ; + +/* set this unconditionally? */ + perf_missing_features.sample_id_all = true; +pr_debug2_peo ("switching off sample_id_all\n" ); + + attr.inherit =1 ; + attr.read_format =PERF_FORMAT_GROUP ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.group_read = true; +pr_debug2_peo ("switching off group read\n" ); + attr.inherit =0 ; + attr.read_format =0 ; + +found: + detection_done = true; + errno = old_errno; + +check: +if ((evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_COUNTERS ) && + perf_missing_features.branch_counters)return true; - }else if (!perf_missing_features.weight_struct && - (evsel->core.attr.sample_type &PERF_SAMPLE_WEIGHT_STRUCT )) { - perf_missing_features.weight_struct = true; -pr_debug2 ("switching off weight struct support\n" ); + +if ((evsel->core.attr.read_format &PERF_FORMAT_LOST ) && + perf_missing_features.read_lost)return true; - }else if (!perf_missing_features.code_page_size && - (evsel->core.attr.sample_type &PERF_SAMPLE_CODE_PAGE_SIZE )) { - perf_missing_features.code_page_size = true; -pr_debug2_peo ("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support, bailing out\n" ); -return false; - }else if (!perf_missing_features.data_page_size && - (evsel->core.attr.sample_type &PERF_SAMPLE_DATA_PAGE_SIZE )) { - perf_missing_features.data_page_size = true; -pr_debug2_peo ("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n" ); -return false; - }else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { - perf_missing_features.cgroup = true; -pr_debug2_peo ("Kernel has no cgroup sampling support, bailing out\n" ); -return false; - }else if (!perf_missing_features.branch_hw_idx && - (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX )) { - perf_missing_features.branch_hw_idx = true; -pr_debug2 ("switching off branch HW index support\n" ); + +if ((evsel->core.attr.sample_type &PERF_SAMPLE_WEIGHT_STRUCT ) && + perf_missing_features.weight_struct)return true; - }else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { - perf_missing_features.aux_output = true; -pr_debug2_peo ("Kernel has no attr.aux_output support, bailing out\n" ); -return false; - }else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) { - perf_missing_features.bpf = true; -pr_debug2_peo ("switching off bpf_event\n" ); + +if (evsel->core.attr.use_clockid && evsel->core.attr.clockid !=CLOCK_MONOTONIC && + !perf_missing_features.clockid) { + perf_missing_features.clockid_wrong = true;return true; - }else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { - perf_missing_features.ksymbol = true; -pr_debug2_peo ("switching off ksymbol\n" ); + } + +if (evsel->core.attr.use_clockid && perf_missing_features.clockid)return true; - }else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { - perf_missing_features.write_backward = true; -pr_debug2_peo ("switching off write_backward\n" ); -return false; - }else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { - perf_missing_features.clockid_wrong = true; -pr_debug2_peo ("switching off clockid\n" ); + +if ((evsel->open_flags &PERF_FLAG_FD_CLOEXEC ) && + perf_missing_features.cloexec)return true; - }else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { - perf_missing_features.clockid = true; -pr_debug2_peo ("switching off use_clockid\n" ); + +if (evsel->core.attr.mmap2 && perf_missing_features.mmap2)return true; - }else if (!perf_missing_features.cloexec && (evsel->open_flags &PERF_FLAG_FD_CLOEXEC )) { - perf_missing_features.cloexec = true; -pr_debug2_peo ("switching off cloexec flag\n" ); + +if ((evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_FLAGS | +PERF_SAMPLE_BRANCH_NO_CYCLES )) && + perf_missing_features.lbr_flags)return true; - }else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { - perf_missing_features.mmap2 = true; -pr_debug2_peo ("switching off mmap2\n" ); + +if (evsel->core.attr.inherit && (evsel->core.attr.read_format &PERF_FORMAT_GROUP ) && + perf_missing_features.group_read)return true; - }else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) { -if (evsel->pmu ==NULL ) - evsel->pmu =evsel__find_pmu (evsel); - -if (evsel->pmu) - evsel->pmu->missing_features.exclude_guest = true; -else { -/* we cannot find PMU, disable attrs now */ - evsel->core.attr.exclude_host = false; - evsel->core.attr.exclude_guest = false; - } -if (evsel->exclude_GH) { -pr_debug2_peo ("PMU has no exclude_host/guest support, bailing out\n" ); -return false; - } -if (!perf_missing_features.exclude_guest) { - perf_missing_features.exclude_guest = true; -pr_debug2_peo ("switching off exclude_guest, exclude_host\n" ); - } +if (evsel->core.attr.ksymbol && perf_missing_features.ksymbol)return true; - }else if (!perf_missing_features.sample_id_all) { - perf_missing_features.sample_id_all = true; -pr_debug2_peo ("switching off sample_id_all\n" ); + +if (evsel->core.attr.bpf_event && perf_missing_features.bpf)return true; - }else if (!perf_missing_features.lbr_flags && - (evsel->core.attr.branch_sample_type & - (PERF_SAMPLE_BRANCH_NO_CYCLES | -PERF_SAMPLE_BRANCH_NO_FLAGS ))) { - perf_missing_features.lbr_flags = true; -pr_debug2_peo ("switching off branch sample type no (cycles/flags)\n" ); + +if ((evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX ) && + perf_missing_features.branch_hw_idx)return true; - }else if (!perf_missing_features.group_read && - evsel->core.attr.inherit && - (evsel->core.attr.read_format &PERF_FORMAT_GROUP ) && -evsel__is_group_leader (evsel)) { - perf_missing_features.group_read = true; -pr_debug2_peo ("switching off group read\n" ); + +if (evsel->core.attr.sample_id_all && perf_missing_features.sample_id_all)return true; - }else { -return false; - } + +return false; } static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,tools/perf/util/evsel.h +0
-2@@ -368,7 +368,6 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,void evsel__close (struct evsel *evsel);int evsel__prepare_open (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads); -bool evsel__detect_missing_features (struct evsel *evsel);bool evsel__precise_ip_fallback (struct evsel *evsel); --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerRe: [PATCH 5/8] perf tools: Detect missing kernel features properly
Quoted 72 lines · Ian Rogers
Quoted 71 lines · Namhyung Kim
The
evsel__detect_missing_features()is to check if the attributes of the evsel is supported or not. But it checks the attribute based on the given evsel, it might miss something if the attr doesn't have the bit or give incorrect results if the event is special.Also it maintains the order of the feature that was added to the kernel which means it can assume older features should be supported once it detects the current feature is working. To minimized the confusion and to accurately check the kernel features, I think it's better to use a software event and go through all the features at once.
Also make the function static since it's only used in
evsel.c.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 345 +++++++++++++++++++++++++++++----------- tools/perf/util/evsel.h | 1 - 2 files changed, 249 insertions(+), 97 deletions(-)tools/perf/util/evsel.c +34
-1@@ -20,6 +20,7 @@#include <linux/zalloc.h> #include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/syscall.h> #include <sys/types.h> #include <dirent.h> #include <stdlib.h> @@ -2150,120 +2151,272 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,return err; } -bool evsel__detect_missing_features (struct evsel *evsel) +static bool has_attr_feature (struct perf_event_attr *attr,unsigned long flags) { +int fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + +if (fd <0 ) { + attr->exclude_kernel =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_hv =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + +if (fd <0 ) { + attr->exclude_guest =1 ; + + fd =syscall (SYS_perf_event_open, attr,/*pid=*/ 0 ,/*cpu=*/ -1 , +/*group_fd=*/ -1 , flags); +close (fd); + } + + attr->exclude_kernel =0 ; + attr->exclude_guest =0 ; + attr->exclude_hv =0 ; +
Quoted 8 lines
tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2191
Quoted 4 lines
tools/perf/util/evsel.c +4
-0+return fd >=0 ; +} + +static void evsel__detect_missing_brstack_features (struct evsel *evsel)In the future could other PMU specific unsupported features be added not just brstack? Perhaps
evsel__detect_missing_pmu_featureswould better capture that.
Yep, sounds reasonable. I think we can add that if we have another thing to check.
Quoted 35 lines
Quoted 35 lines
tools/perf/util/evsel.c +21
-10+{ +static bool detection_done = false; +struct perf_event_attr attr = { + .type = evsel->core.attr.type, + .config = evsel->core.attr.config, + .disabled =1 , + .sample_type =PERF_SAMPLE_BRANCH_STACK , + .sample_period =1000 , + }; +int old_errno; + +if (detection_done) +return ; + + old_errno = errno; +/* * Must probe features in the order they were added to the -* perf_event_attr interface. +* perf_event_attr interface. These are PMU specific limitation +* so we can detect with the given hardware event and stop on the +* first one succeeded. */ -if (!perf_missing_features.branch_counters && - (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_COUNTERS )) { - perf_missing_features.branch_counters = true; -pr_debug2 ("switching off branch counters support\n" ); -return true; - }else if (!perf_missing_features.read_lost && - (evsel->core.attr.read_format &PERF_FORMAT_LOST )) { - perf_missing_features.read_lost = true; -pr_debug2 ("switching off PERF_FORMAT_LOST support\n" ); + +/* Please add new feature detection here. */
Quoted 8 lines
tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2220
Quoted 5 lines
tools/perf/util/evsel.c +5
-0+ + attr.branch_sample_type =PERF_SAMPLE_BRANCH_COUNTERS ; +if (has_attr_feature (&attr,/*flags=*/ 0 )) + goto found; + perf_missing_features.branch_counters = true;It feels like these global variables should be part of the PMU state. There is already perf_pmu.missing_features.
You're right. But I think this is kinda global feature unless we have different PMUs that provide different branch sampling capability. It's just the feature test requires a specific PMU and event. But it'd be better putting this into struct perf_pmu later.
Kan, can you confirm if Intel hybrid systems have the same branch stack sampling capabilities on both cores?
Thanks,
Namhyung
Re: [PATCH 5/8] perf tools: Detect missing kernel features properly
In reply to Namhyung KimQuoted 10 lines
tools/perf/util/evsel.c +0
-10- }else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) { -if (evsel->pmu ==NULL ) - evsel->pmu =evsel__find_pmu (evsel); - -if (evsel->pmu) - evsel->pmu->missing_features.exclude_guest = true; -else { -/* we cannot find PMU, disable attrs now */ - evsel->core.attr.exclude_host = false; - evsel->core.attr.exclude_guest = false;
tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2244
Quoted 10 lines
tools/perf/util/evsel.c +0
-9- } -if (evsel->exclude_GH) { -pr_debug2_peo ("PMU has no exclude_host/guest support, bailing out\n" ); -return false; - } -if (!perf_missing_features.exclude_guest) { - perf_missing_features.exclude_guest = true; -pr_debug2_peo ("switching off exclude_guest, exclude_host\n" ); - }
Shall we get rid of:
perf_missing_features.exclude_guest
pmu->missing_features.exclude_guest
they don't seem to be used anywhere after the patch.
Thanks,
Ravi
Namhyung Kim
maintainerRe: [PATCH 5/8] perf tools: Detect missing kernel features properly
Quoted 23 lines · Ravi Bangoria
Quoted 10 lines
tools/perf/util/evsel.c +0
-10- }else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) { -if (evsel->pmu ==NULL ) - evsel->pmu =evsel__find_pmu (evsel); - -if (evsel->pmu) - evsel->pmu->missing_features.exclude_guest = true; -else { -/* we cannot find PMU, disable attrs now */ - evsel->core.attr.exclude_host = false; - evsel->core.attr.exclude_guest = false;tools/perf/util/evsel.c int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2244
Quoted 10 lines
tools/perf/util/evsel.c +0
-9- } -if (evsel->exclude_GH) { -pr_debug2_peo ("PMU has no exclude_host/guest support, bailing out\n" ); -return false; - } -if (!perf_missing_features.exclude_guest) { - perf_missing_features.exclude_guest = true; -pr_debug2_peo ("switching off exclude_guest, exclude_host\n" ); - }Shall we get rid of:
Quoted 4 lines
perf_missing_features.exclude_guest
pmu->missing_features.exclude_guestthey don't seem to be used anywhere after the patch.
Hmm.. it's my bad. I think we should keep it for ancient kernels.
Thanks,
Namhyung
Namhyung Kim
maintainerPATCH 6/8 perf tools: Move x86__is_amd_cpu() to util/env.c
In reply to Namhyung KimIt can be called from non-x86 platform so let's move it to the general util directory. Also add a new helper perf_env__is_x86_amd_cpu() so that it can be called with an existing perf_env as well.
--- tools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 ------------------- tools/perf/arch/x86/util/env.h | 7 ------- tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/util/env.c | 24 ++++++++++++++++++++++++ tools/perf/util/env.h | 4 ++++ 6 files changed, 29 insertions(+), 28 deletions(-) delete mode 100644 tools/perf/arch/x86/util/env.c delete mode 100644 tools/perf/arch/x86/util/env.h
tools/perf/arch/x86/util/Build +0 -1
@@ -10,7 +10,6 @@ perf-util-y += evlist.o perf-util-y += mem-events.o perf-util-y += evsel.o perf-util-y += iostat.o -perf-util-y += env.o perf-util-$(CONFIG_DWARF) += dwarf-regs.o perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
tools/perf/arch/x86/util/env.c deleted +0 -19
@@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "linux/string.h" -#include "util/env.h" -#include "env.h" - -bool x86__is_amd_cpu (void ) -{ -struct perf_env env = { .total_mem =0 , }; -static int is_amd;/* 0: Uninitialized, 1: Yes, -1: No */ - -if (is_amd) - goto ret; - -perf_env__cpuid (&env); - is_amd = env.cpuid &&strstarts (env.cpuid,"AuthenticAMD" ) ?1 :-1 ; -perf_env__exit (&env); -ret: -return is_amd >=1 ? true : false; -}
tools/perf/arch/x86/util/env.h deleted +0 -7
@@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _X86_ENV_H -#define _X86_ENV_H - -bool x86__is_amd_cpu (void ); - -#endif /* _X86_ENV_H */
tools/perf/arch/x86/util/pmu.c +1 -1
@@ -16,7 +16,7 @@#include "../../../util/fncache.h" #include "../../../util/pmus.h" #include "mem-events.h" -#include "env.h" +#include "util/env.h" void perf_pmu__arch_init (struct perf_pmu *pmu__maybe_unused ) {
tools/perf/util/env.c +24 -0
@@ -5,6 +5,7 @@#include "util/header.h" #include "linux/compiler.h" #include <linux/ctype.h> +#include <linux/string.h> #include <linux/zalloc.h> #include "cgroup.h" #include <errno.h>
@@ -625,6 +626,7 @@ char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,return NULL ; } +void perf_env__find_br_cntr_info (struct perf_env *env,unsigned int *nr,unsigned int *width)
@@ -639,3 +641,25 @@ void perf_env__find_br_cntr_info(struct perf_env *env, env->pmu_caps->br_cntr_width; } } + +bool perf_env__is_x86_amd_cpu (struct perf_env *env) +{ +static int is_amd;/* 0: Uninitialized, 1: Yes, -1: No */ + +if (is_amd ==0 ) + is_amd = env->cpuid &&strstarts (env->cpuid,"AuthenticAMD" ) ?1 :-1 ; + +return is_amd >=1 ? true : false; +} + +bool x86__is_amd_cpu (void ) +{ +struct perf_env env = { .total_mem =0 , }; +bool is_amd; + +perf_env__cpuid (&env); + is_amd =perf_env__is_x86_amd_cpu (&env); +perf_env__exit (&env); + +return is_amd; +}
tools/perf/util/env.h +4 -0
@@ -195,4 +195,8 @@ bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);void perf_env__find_br_cntr_info (struct perf_env *env,unsigned int *nr,unsigned int *width); + +bool x86__is_amd_cpu (void ); +bool perf_env__is_x86_amd_cpu (struct perf_env *env); +#endif /* __PERF_ENV_H */
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 6/8] perf tools: Move x86__is_amd_cpu() to util/env.c
Quoted 92 lines · Namhyung Kim
It can be called from non-x86 platform so let's move it to the general util directory. Also add a new helper
perf_env__is_x86_amd_cpu()so that it can be called with an existingperf_envas well.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 ------------------- tools/perf/arch/x86/util/env.h | 7 ------- tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/util/env.c | 24 ++++++++++++++++++++++++ tools/perf/util/env.h | 4 ++++ 6 files changed, 29 insertions(+), 28 deletions(-) delete mode 100644 tools/perf/arch/x86/util/env.c delete mode 100644 tools/perf/arch/x86/util/env.htools/perf/arch/x86/util/Build +0
-1@@ -10,7 +10,6 @@ perf-util-y += evlist.o perf-util-y += mem-events.o perf-util-y += evsel.o perf-util-y += iostat.o -perf-util-y += env.o perf-util-$(CONFIG_DWARF) += dwarf-regs.o perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.otools/perf/arch/x86/util/env.c deleted +0
-19@@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "linux/string.h" -#include "util/env.h" -#include "env.h" - -bool x86__is_amd_cpu (void ) -{ -struct perf_env env = { .total_mem =0 , }; -static int is_amd;/* 0: Uninitialized, 1: Yes, -1: No */ - -if (is_amd) - goto ret; - -perf_env__cpuid (&env); - is_amd = env.cpuid &&strstarts (env.cpuid,"AuthenticAMD" ) ?1 :-1 ; -perf_env__exit (&env); -ret: -return is_amd >=1 ? true : false; -}tools/perf/arch/x86/util/env.h deleted +0
-7@@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _X86_ENV_H -#define _X86_ENV_H - -bool x86__is_amd_cpu (void ); - -#endif /* _X86_ENV_H */ tools/perf/arch/x86/util/pmu.c +1
-1@@ -16,7 +16,7 @@#include "../../../util/fncache.h" #include "../../../util/pmus.h" #include "mem-events.h" -#include "env.h" +#include "util/env.h" void perf_pmu__arch_init (struct perf_pmu *pmu__maybe_unused ) {tools/perf/util/env.c +1
-0@@ -5,6 +5,7 @@#include "util/header.h" #include "linux/compiler.h" #include <linux/ctype.h> +#include <linux/string.h> #include <linux/zalloc.h> #include "cgroup.h" #include <errno.h>
tools/perf/util/env.c char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, · line 629
Quoted 4 lines
tools/perf/util/env.c +1
-0@@ -625,6 +626,7 @@ char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,return NULL ; } +
Useless empty line.
Thanks,
Kan
Quoted 42 lines
tools/perf/util/env.c +22
-0void perf_env__find_br_cntr_info (struct perf_env *env,unsigned int *nr,unsigned int *width)@@ -639,3 +641,25 @@ void perf_env__find_br_cntr_info(struct perf_env *env, env->pmu_caps->br_cntr_width; } } + +bool perf_env__is_x86_amd_cpu (struct perf_env *env) +{ +static int is_amd;/* 0: Uninitialized, 1: Yes, -1: No */ + +if (is_amd ==0 ) + is_amd = env->cpuid &&strstarts (env->cpuid,"AuthenticAMD" ) ?1 :-1 ; + +return is_amd >=1 ? true : false; +} + +bool x86__is_amd_cpu (void ) +{ +struct perf_env env = { .total_mem =0 , }; +bool is_amd; + +perf_env__cpuid (&env); + is_amd =perf_env__is_x86_amd_cpu (&env); +perf_env__exit (&env); + +return is_amd; +}tools/perf/util/env.h +4
-0@@ -195,4 +195,8 @@ bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);void perf_env__find_br_cntr_info (struct perf_env *env,unsigned int *nr,unsigned int *width); + +bool x86__is_amd_cpu (void ); +bool perf_env__is_x86_amd_cpu (struct perf_env *env); +#endif /* __PERF_ENV_H */
Namhyung Kim
maintainerRe: [PATCH 6/8] perf tools: Move x86__is_amd_cpu() to util/env.c
Quoted 98 lines · Kan
Quoted 95 lines · Namhyung Kim
It can be called from non-x86 platform so let's move it to the general util directory. Also add a new helper
perf_env__is_x86_amd_cpu()so that it can be called with an existingperf_envas well.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 ------------------- tools/perf/arch/x86/util/env.h | 7 ------- tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/util/env.c | 24 ++++++++++++++++++++++++ tools/perf/util/env.h | 4 ++++ 6 files changed, 29 insertions(+), 28 deletions(-) delete mode 100644 tools/perf/arch/x86/util/env.c delete mode 100644 tools/perf/arch/x86/util/env.htools/perf/arch/x86/util/Build +0
-1@@ -10,7 +10,6 @@ perf-util-y += evlist.o perf-util-y += mem-events.o perf-util-y += evsel.o perf-util-y += iostat.o -perf-util-y += env.o perf-util-$(CONFIG_DWARF) += dwarf-regs.o perf-util-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.otools/perf/arch/x86/util/env.c deleted +0
-19@@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "linux/string.h" -#include "util/env.h" -#include "env.h" - -bool x86__is_amd_cpu (void ) -{ -struct perf_env env = { .total_mem =0 , }; -static int is_amd;/* 0: Uninitialized, 1: Yes, -1: No */ - -if (is_amd) - goto ret; - -perf_env__cpuid (&env); - is_amd = env.cpuid &&strstarts (env.cpuid,"AuthenticAMD" ) ?1 :-1 ; -perf_env__exit (&env); -ret: -return is_amd >=1 ? true : false; -}tools/perf/arch/x86/util/env.h deleted +0
-7@@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _X86_ENV_H -#define _X86_ENV_H - -bool x86__is_amd_cpu (void ); - -#endif /* _X86_ENV_H */ tools/perf/arch/x86/util/pmu.c +1
-1@@ -16,7 +16,7 @@#include "../../../util/fncache.h" #include "../../../util/pmus.h" #include "mem-events.h" -#include "env.h" +#include "util/env.h" void perf_pmu__arch_init (struct perf_pmu *pmu__maybe_unused ) {tools/perf/util/env.c +1
-0@@ -5,6 +5,7 @@#include "util/header.h" #include "linux/compiler.h" #include <linux/ctype.h> +#include <linux/string.h> #include <linux/zalloc.h> #include "cgroup.h" #include <errno.h> @@ -625,6 +626,7 @@ char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,return NULL ; }
Quoted 3 lines
tools/perf/util/env.c char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, · line 629
Quoted 1 line
tools/perf/util/env.c +1
-0+Useless empty line.
Ugh, will remove.
Thanks,
Namhyung
Namhyung Kim
maintainerPATCH 7/8 perf tools: Check fallback error and order
In reply to Namhyung KimThe perf_event_open might fail due to various reasons, so blindly reducing precise_ip level might not be the best way to deal with it.
It seems the kernel return -EOPNOTSUPP when PMU doesn't support the given precise level. Let's try again with the correct error code.
This caused a problem on AMD, as it stops on precise_ip of 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add the evsel__handle_error_quirks() to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.
--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)
tools/perf/util/evsel.c +21 -6
@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ +if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) { + evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)
@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */
@@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread;
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Ian Rogers
reviewerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0
tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */
Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2426
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {
So here rather than x86__is_amd_cpu it would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic into pmu.c.
Thanks,
Ian
Quoted 44 lines
tools/perf/util/evsel.c +16
-7+ evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 35 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 6 lines
tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2426
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.
I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have precise_ip. So it might have just core pmu (or no pmu) in the evsel.
Thanks,
Namhyung
Quoted 45 lines
Quoted 45 lines
tools/perf/util/evsel.c +16
-7+ evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.46.1.824.gd892dcdcdd-goog
Ian Rogers
reviewerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {
Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always use perf_pmus__scan_core(NULL) or perf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW). evsel->pmu->is_core && x86__is_amd_cpu() would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.
Thanks,
Ian
Quoted 45 lines
Quoted 45 lines
Quoted 45 lines
tools/perf/util/evsel.c +16
-7+ evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 49 lines · Ian Rogers
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.
Quoted 8 lines
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always useperf_pmus__scan_core(NULL)orperf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW).evsel->pmu->is_core&&x86__is_amd_cpu()would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.
But IBS is the only PMU on AMD that provides precise_ip IIRC. So I don't think other events would have it nor have any effect on changing the value. So maybe we can skip the PMU scanning and just drop to 0?
Thanks,
Namhyung
Quoted 46 lines
Quoted 46 lines
Quoted 46 lines
Quoted 46 lines
tools/perf/util/evsel.c +16
-7+ evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.46.1.824.gd892dcdcdd-goog
Ian Rogers
reviewerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 60 lines · Namhyung Kim
Quoted 49 lines · Ian Rogers
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.Quoted 8 lines
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always useperf_pmus__scan_core(NULL)orperf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW).evsel->pmu->is_core&&x86__is_amd_cpu()would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.
Quoted 3 lines
But IBS is the only PMU on AMD that provides
precise_ipIIRC. So I don't think other events would have it nor have any effect on changing the value. So maybe we can skip the PMU scanning and just drop to 0?
cpu supports precise_ip as it forwards it to IBS, IBS is an ambiguous term as there are ibs_op and ibs_fetch PMUs. The code is using values in the attribute to infer the PMU that is being used, it feels it would be more intention revealing to do things like:
```
if (error == ... && perf_pmu__is_ibs_op_or_fetch(evsel->pmu)) ..
```
perhaps to not burden the code this can be:
```
if (...) {
assert(perf_pmu__is_ibs_op_or_fetch(evsel->pmu));
```Thanks,
Ian
Quoted 46 lines
Quoted 46 lines
Quoted 46 lines
Quoted 46 lines
Quoted 46 lines
tools/perf/util/evsel.c +16
-7+ evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2580,9 +2594,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2599,11 +2610,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.46.1.824.gd892dcdcdd-goog
Namhyung Kim
maintainerRe: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 65 lines · Ian Rogers
Quoted 60 lines · Namhyung Kim
Quoted 49 lines · Ian Rogers
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.Quoted 8 lines
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always useperf_pmus__scan_core(NULL)orperf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW).evsel->pmu->is_core&&x86__is_amd_cpu()would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.Quoted 3 lines
But IBS is the only PMU on AMD that provides
precise_ipIIRC. So I don't think other events would have it nor have any effect on changing the value. So maybe we can skip the PMU scanning and just drop to 0?
Quoted 7 lines
cpu supports
precise_ipas it forwards it to IBS, IBS is an ambiguous term as there areibs_opandibs_fetchPMUs. The code is using values in the attribute to infer the PMU that is being used, it feels it would be more intention revealing to do things like:``` if (error == ... && perf_pmu__is_ibs_op_or_fetch(evsel->pmu)) .. ```
I guess it'd get a core PMU for the default cycles event. I think the intention is already confusing with the implicit forwarding.
Thanks,
Namhyung
Quoted 8 lines
perhaps to not burden the code this can be:
``` if (...) { assert(perf_pmu__is_ibs_op_or_fetch(evsel->pmu)); ```Thanks,
Ian
Namhyung Kim
maintainerRe: [PATCH 7/8] perf tools: Check fallback error and order
Hi Ian,
Quoted 74 lines · Namhyung Kim
Quoted 65 lines · Ian Rogers
Quoted 60 lines · Namhyung Kim
Quoted 49 lines · Ian Rogers
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.Quoted 8 lines
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always useperf_pmus__scan_core(NULL)orperf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW).evsel->pmu->is_core&&x86__is_amd_cpu()would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.Quoted 3 lines
But IBS is the only PMU on AMD that provides
precise_ipIIRC. So I don't think other events would have it nor have any effect on changing the value. So maybe we can skip the PMU scanning and just drop to 0?Quoted 7 lines
cpu supports
precise_ipas it forwards it to IBS, IBS is an ambiguous term as there areibs_opandibs_fetchPMUs. The code is using values in the attribute to infer the PMU that is being used, it feels it would be more intention revealing to do things like:``` if (error == ... && perf_pmu__is_ibs_op_or_fetch(evsel->pmu)) .. ```
Quoted 2 lines
I guess it'd get a core PMU for the default cycles event. I think the intention is already confusing with the implicit forwarding.
What about this?
---8<---
From 70d39fb5c2956ba264a292f112f7fd7272dc91be Mon Sep 17 00:00:00 2001
From: Namhyung Kim <[email protected]>
Date: Tue, 3 Sep 2024 22:50:09 -0700
Subject: [PATCH] perf tools: Check fallback error and order
The perf_event_open might fail due to various reasons, so blindly reducing precise_ip level might not be the best way to deal with it.
It seems the kernel return -EOPNOTSUPP when PMU doesn't support the given precise level. Let's try again with the correct error code.
This caused a problem on AMD, as it stops on precise_ip of 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add the evsel__handle_error_quirks() to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.
--- tools/perf/util/evsel.c | 50 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 44 insertions(+), 6 deletions(-)
tools/perf/util/evsel.c +44 -6
@@ -2246,6 +2246,43 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +/* +* AMD core PMU forwards some events with precise_ip to IBS implicitly. +* This logic matches to the kernel function (core_pmu_ibs_config). +*/ +static bool evsel__is_implicit_ibs_event (struct evsel *evsel) +{ +if (evsel->core.attr.precise_ip ==0 || !x86__is_amd_cpu ()) +return false; + +if (evsel->core.attr.type ==PERF_TYPE_HARDWARE && + evsel->core.attr.config ==PERF_COUNT_HW_CPU_CYCLES ) +return true; + +if (evsel->core.attr.type ==PERF_TYPE_RAW && + (evsel->core.attr.config ==0x76 || evsel->core.attr.config ==0xc1 )) +return true; + +return false; +} + +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* +* AMD IBS doesn't support exclude_kernel, forward it back to the core +* PMU by clearing precise_ip only if it's from precise_max (:P). +*/ +if (error == -EINVAL &&evsel__is_implicit_ibs_event (evsel) && + evsel->core.attr.exclude_kernel && evsel->precise_max) { + evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)
@@ -2366,9 +2403,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */
@@ -2385,11 +2419,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread;
Signature · 1 line
2.47.0.rc1.288.g06298d1525-goog
Re: [PATCH 7/8] perf tools: Check fallback error and order
Quoted 11 lines
tools/perf/util/evsel.c +0
-3@@ -2366,9 +2403,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */
tools/perf/util/evsel.c static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2423
Quoted 7 lines
tools/perf/util/evsel.c +2
-2@@ -2385,11 +2419,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open;
This will change the behavior of events like instructions:P on AMD.
Without patch:
$ ./perf record -e instructions:P -- true [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.009 MB perf.data (9 samples) ]
With the patch:
$ ./perf record -e instructions:P -- true Error: The instructions:Pu event is not supported.
Thanks,
Ravi
Namhyung Kim
maintainerRe: [PATCH 7/8] perf tools: Check fallback error and order
Hello Ravi,
Quoted 26 lines · Ravi Bangoria
Quoted 11 lines
tools/perf/util/evsel.c +0
-3@@ -2366,9 +2403,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ tools/perf/util/evsel.c static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, · line 2423
Quoted 7 lines
tools/perf/util/evsel.c +2
-2@@ -2385,11 +2419,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open;This will change the behavior of events like instructions:P on AMD.
Without patch:
$ ./perf record -e instructions:P -- true [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.009 MB perf.data (9 samples) ]
Quoted 5 lines
With the patch:
$ ./perf record -e instructions:P -- true Error: The instructions:Pu event is not supported.
Thanks for the test, it should support other events too. I've noticed it returns -ENOENT for non-IBS events with precise_ip > 0. Will handle them as well.
Thanks,
Namhyung
Ian Rogers
reviewerRe: [PATCH 7/8] perf tools: Check fallback error and order
In reply to Namhyung KimQuoted 117 lines · Namhyung Kim
Hi Ian,
Quoted 74 lines · Namhyung Kim
Quoted 65 lines · Ian Rogers
Quoted 60 lines · Namhyung Kim
Quoted 49 lines · Ian Rogers
Quoted 40 lines · Namhyung Kim
Quoted 38 lines · Ian Rogers
Quoted 23 lines · Namhyung Kim
The
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +0
-0tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2424
Quoted 6 lines
tools/perf/util/evsel.c +3
-0@@ -2419,6 +2419,20 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* AMD IBS doesn't support exclude_kernel, forward it to core PMU */ Should the quirk handling be specific to evsels with the IBS PMU given the comment above? ie this is a PMU specific workaround rather than an AMD specific workaround, however, the PMU only exists on AMD :-)
Quoted 2 lines
tools/perf/util/evsel.c +2
-0+if (error == -EINVAL && evsel->precise_max && evsel->core.attr.precise_ip && + evsel->core.attr.exclude_kernel &&x86__is_amd_cpu ()) {Quoted 7 lines
Quoted 3 lines
So here rather than
x86__is_amd_cpuit would be !strcmp(evsel->pmu->name, "ibs_...") . But it may be cleaner to move the logic intopmu.c.I guess the problem is that AMD driver does implicit forwarding to IBS if the legacy hardware events have
precise_ip. So it might have just core pmu (or no pmu) in the evsel.Quoted 8 lines
I think the no PMU case should probably have a PMU possibly similar to the tool PMU in:
https://lore.kernel.org/all/[email protected]/
But that's not in place yet. You can always useperf_pmus__scan_core(NULL)orperf_pmus__find_by_type(evsel->core.attr.type or PERF_TYPE_RAW).evsel->pmu->is_core&&x86__is_amd_cpu()would identify an AMD core PMU whereas the code above could fire for IBS or other PMUs.Quoted 3 lines
But IBS is the only PMU on AMD that provides
precise_ipIIRC. So I don't think other events would have it nor have any effect on changing the value. So maybe we can skip the PMU scanning and just drop to 0?Quoted 7 lines
cpu supports
precise_ipas it forwards it to IBS, IBS is an ambiguous term as there areibs_opandibs_fetchPMUs. The code is using values in the attribute to infer the PMU that is being used, it feels it would be more intention revealing to do things like:``` if (error == ... && perf_pmu__is_ibs_op_or_fetch(evsel->pmu)) .. ```Quoted 2 lines
I guess it'd get a core PMU for the default cycles event. I think the intention is already confusing with the implicit forwarding.
What about this?
---8<---
From
70d39fb5c2956ba264a292f112f7fd7272dc91beMon Sep 17 00:00:00 2001
From: Namhyung Kim <[email protected]>
Date: Tue, 3 Sep 2024 22:50:09 -0700
Subject: [PATCH] perf tools: Check fallback error and orderThe
perf_event_openmight fail due to various reasons, so blindly reducingprecise_iplevel might not be the best way to deal with it.It seems the kernel return
-EOPNOTSUPPwhen PMU doesn't support the given precise level. Let's try again with the correct error code.This caused a problem on AMD, as it stops on
precise_ipof 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add theevsel__handle_error_quirks()to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS.Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/evsel.c | 50 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 44 insertions(+), 6 deletions(-)tools/perf/util/evsel.c +2
-0@@ -2246,6 +2246,43 @@ static bool evsel__detect_missing_features(struct evsel *evsel)return false; } +/* +* AMD core PMU forwards some events with precise_ip to IBS implicitly.
tools/perf/util/evsel.c static bool evsel__detect_missing_features(struct evsel *evsel) · line 2260
Quoted 10 lines
tools/perf/util/evsel.c +10
-0+* This logic matches to the kernel function (core_pmu_ibs_config). +*/ +static bool evsel__is_implicit_ibs_event (struct evsel *evsel) +{ +if (evsel->core.attr.precise_ip ==0 || !x86__is_amd_cpu ()) +return false; + +if (evsel->core.attr.type ==PERF_TYPE_HARDWARE && + evsel->core.attr.config ==PERF_COUNT_HW_CPU_CYCLES ) +return true;
Lgtm, still seems strange we're not asserting something like evsel->is_pmu_core. There's some clean up of that in (unmerged):
https://lore.kernel.org/lkml/[email protected]/#t
Thanks,
Ian
Quoted 60 lines
tools/perf/util/evsel.c +32
-7+ +if (evsel->core.attr.type ==PERF_TYPE_RAW && + (evsel->core.attr.config ==0x76 || evsel->core.attr.config ==0xc1 )) +return true; + +return false; +} + +static bool evsel__handle_error_quirks (struct evsel *evsel,int error) +{ +/* +* AMD IBS doesn't support exclude_kernel, forward it back to the core +* PMU by clearing precise_ip only if it's from precise_max (:P). +*/ +if (error == -EINVAL &&evsel__is_implicit_ibs_event (evsel) && + evsel->core.attr.exclude_kernel && evsel->precise_max) { + evsel->core.attr.precise_ip =0 ; +pr_debug2_peo ("removing precise_ip on AMD\n" ); +display_attr (&evsel->core.attr); +return true; + } + +return false; +} +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus,struct perf_thread_map *threads,int start_cpu_map_idx,int end_cpu_map_idx)@@ -2366,9 +2403,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,return 0 ; try_fallback: -if (evsel__precise_ip_fallback (evsel)) - goto retry_open; -if (evsel__ignore_missing_thread (evsel,perf_cpu_map__nr (cpus), idx, threads, thread, err)) {/* We just removed 1 thread, so lower the upper nthreads limit. */ @@ -2385,11 +2419,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,if (err == -EMFILE &&rlimit__increase_nofile (&set_rlimit)) goto retry_open; -if (err != -EINVAL || idx >0 || thread >0 ) - goto out_close; +if (err == -EOPNOTSUPP &&evsel__precise_ip_fallback (evsel)) + goto retry_open; -if (evsel__detect_missing_features (evsel)) +if (err == -EINVAL &&evsel__detect_missing_features (evsel)) goto fallback_missing_features; + +if (evsel__handle_error_quirks (evsel, err)) + goto retry_open; + out_close:if (err) threads->err_thread = thread; --2.47.0.rc1.288.g06298d1525-goog
Namhyung Kim
maintainerPATCH 8/8 perf record: Just use "cycles:P" as the default event
In reply to Namhyung KimThe fallback logic can add ":u" modifier if needed.
--- tools/perf/builtin-record.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
tools/perf/builtin-record.c +1 -3
@@ -4157,9 +4157,7 @@ int cmd_record(int argc, const char **argv) record.opts.tail_synthesize = true;if (rec->evlist->core.nr_entries ==0 ) { -bool can_profile_kernel =perf_event_paranoid_check (1 ); - - err =parse_event (rec->evlist, can_profile_kernel ?"cycles:P" :"cycles:Pu" ); + err =parse_event (rec->evlist,"cycles:P" );if (err) goto out; }
Signature · 1 line
2.46.1.824.gd892dcdcdd-goog
Re: [PATCH 8/8] perf record: Just use "cycles:P" as the default event
Quoted 4 lines · Namhyung Kim
The fallback logic can add ":u" modifier if needed.
Signed-off-by Namhyung Kim <[email protected]>
Thanks,
Ian
Quoted 22 lines
--- tools/perf/builtin-record.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)tools/perf/builtin-record.c +1
-4@@ -4157,9 +4157,7 @@ int cmd_record(int argc, const char **argv) record.opts.tail_synthesize = true;if (rec->evlist->core.nr_entries ==0 ) { -bool can_profile_kernel =perf_event_paranoid_check (1 ); - - err =parse_event (rec->evlist, can_profile_kernel ?"cycles:P" :"cycles:Pu" ); + err =parse_event (rec->evlist,"cycles:P" );if (err) goto out; } --2.46.1.824.gd892dcdcdd-goog
Quoted 49 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
Namhyung
Quoted 10 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default event
The patch set looks good to me.
Thanks,
Kan
Quoted 22 lines
tools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-) delete mode 100644 tools/perf/arch/x86/util/env.c delete mode 100644 tools/perf/arch/x86/util/env.h
Namhyung Kim
maintainerQuoted 63 lines · Kan
Quoted 49 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
NamhyungQuoted 10 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default event
Quoted 3 lines
The patch set looks good to me.
Acked-by Kan Liang <[email protected]>
Thanks for your review!
Namhyung
Quoted 42 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
Quoted 7 lines
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
Namhyung
Looks like you need to allow for :H in the perf stat test on M1 now:
tools/perf/tests/shell/stat.sh +1 -1
@@ -161,7 +161,7 @@ test_hybrid() { fi # Run default Perf stat - cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles " | wc -l) + cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles | cycles:H " | wc -l) if [ "$pmus" -ne "$cycles_events" ] then
Other than that:
Quoted 32 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default eventtools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-)delete mode 100644
tools/perf/arch/x86/util/env.cdelete mode 100644tools/perf/arch/x86/util/env.h
Namhyung Kim
maintainerQuoted 60 lines · James Clark
Quoted 42 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
Quoted 7 lines
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
NamhyungLooks like you need to allow for :H in the perf stat test on M1 now:
tools/perf/tests/shell/stat.sh +0
-0
tools/perf/tests/shell/stat.sh test_hybrid() { · line 165
Quoted 6 lines
tools/perf/tests/shell/stat.sh +1
-1@@ -161,7 +161,7 @@ test_hybrid() { fi # Run default Perf stat - cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles " | wc -l) + cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles | cycles:H " | wc -l)
Ok, what about "u"? Probably it can be
cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/(uH)*| cycles(:[uH])* " | wc -l)
Quoted 7 lines
tools/perf/tests/shell/stat.sh +0
-0if [ "$pmus" -ne "$cycles_events" ] thenOther than that:
Reviewed-by James Clark <[email protected]>
Thanks for the review!
Namhyung
Quoted 34 lines
Quoted 33 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default eventtools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-)delete mode 100644
tools/perf/arch/x86/util/env.cdelete mode 100644tools/perf/arch/x86/util/env.h
James Clark
reviewerQuoted 63 lines · Namhyung Kim
Quoted 62 lines · James Clark
Quoted 42 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
Quoted 7 lines
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
NamhyungLooks like you need to allow for :H in the perf stat test on M1 now:
tools/perf/tests/shell/stat.sh +0
-0@@ -161,7 +161,7 @@ test_hybrid() { fi
Quoted 9 lines
tools/perf/tests/shell/stat.sh test_hybrid() { · line 164
Quoted 4 lines
tools/perf/tests/shell/stat.sh +1
-1# Run default Perf stat - cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles " | wc -l) + cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles | cycles:H " | wc -l)Ok, what about "u"? Probably it can be
cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/(uH)*| cycles(:[uH])* " | wc -l)
Yep that probably works too and is a bit more robust
Quoted 45 lines
Quoted 7 lines
tools/perf/tests/shell/stat.sh +0
-0if [ "$pmus" -ne "$cycles_events" ] thenOther than that:
Reviewed-by James Clark <[email protected]>Thanks for the review!
NamhyungQuoted 34 lines
Quoted 33 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default eventtools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-)delete mode 100644
tools/perf/arch/x86/util/env.cdelete mode 100644tools/perf/arch/x86/util/env.h
Namhyung Kim
maintainerQuoted 73 lines · James Clark
Quoted 70 lines · Namhyung Kim
Quoted 60 lines · James Clark
Quoted 42 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
Quoted 7 lines
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThanks,
NamhyungLooks like you need to allow for :H in the perf stat test on M1 now:
tools/perf/tests/shell/stat.sh +0
-0tools/perf/tests/shell/stat.sh test_hybrid() { · line 165
Quoted 6 lines
tools/perf/tests/shell/stat.sh +1
-1@@ -161,7 +161,7 @@ test_hybrid() { fi # Run default Perf stat - cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles " | wc -l) + cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/| cycles | cycles:H " | wc -l)Ok, what about "u"? Probably it can be
Quoted 4 lines
Quoted 2 lines
cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/(uH)*| cycles(:[uH])* " | wc -l)Yep that probably works too and is a bit more robust
Great, I'll merge this change with the fix above if nobody objects. It'd be nice if more folks on other architectures could test this patchset too.
Thanks,
Namhyung
Quoted 46 lines
Quoted 46 lines
Quoted 8 lines
tools/perf/tests/shell/stat.sh +0
-0if [ "$pmus" -ne "$cycles_events" ] thenOther than that:
Reviewed-by James Clark <[email protected]>Thanks for the review!
NamhyungQuoted 34 lines
Quoted 33 lines
Namhyung Kim (8):
perf tools: Add fallback forexclude_guestperf tools: Don't set attr.exclude_guest by default perf tools: Simplifyevsel__add_modifier()perf tools: Do not setexclude_guestforprecise_ipperf tools: Detect missing kernel features properly perf tools: Movex86__is_amd_cpu()toutil/env.cperf tools: Check fallback error and order perf record: Just use "cycles:P" as the default eventtools/perf/arch/x86/util/Build | 1 - tools/perf/arch/x86/util/env.c | 19 - tools/perf/arch/x86/util/env.h | 7 - tools/perf/arch/x86/util/pmu.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/builtin-record.c | 4 +- tools/perf/builtin-stat.c | 18 +- tools/perf/dlfilters/dlfilter-test-api-v0.c | 2 +- tools/perf/dlfilters/dlfilter-test-api-v2.c | 2 +- tools/perf/tests/attr/test-record-dummy-C0 | 2 +- tools/perf/tests/parse-events.c | 30 +- tools/perf/util/env.c | 24 ++ tools/perf/util/env.h | 4 + tools/perf/util/evsel.c | 394 ++++++++++++++------ tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 6 +- tools/perf/util/util.c | 10 +- tools/perf/util/util.h | 3 + 18 files changed, 364 insertions(+), 166 deletions(-)delete mode 100644
tools/perf/arch/x86/util/env.cdelete mode 100644tools/perf/arch/x86/util/env.h
Quoted 37 lines · Namhyung Kim
Hello,
I found perf tools set
exclude_guestbit inconsistently. It used to set the bit but now the default event for perf record doesn't. So I'm wondering why we want the bit in the first place.Actually it's not good for PMUs don't support any exclusion like AMD IBS because it disables new features after the
exclude_guestdue to the missing feature detection logic.v4 changes)
* handle EOPNOTSUPP error in compatible way (Kan)
* drop --exclude-guest option in perf stat
* not to separateexclude_hvfallback
* rename toexclude_GH_default(Kan)
* drop the RFC from the subjectv3) https://lore.kernel.org/lkml/[email protected]/
* move
exclude_guestfallback to the front
* fixprecise_maxhandling on AMD
* simplify the default event for perf recordv2) https://lore.kernel.org/lkml/[email protected]/
* update the missing feature detection logic
* separateexclude_hvfallback
* add new fallback forexclude_guestv1) https://lore.kernel.org/lkml/[email protected]/
AFAIK it doesn't matter for the most cases but perf kvm. If users need to set the bit, they can still use :H modifier. For vPMU pass- through or Apple M1, it'd add the
exclude_guestduring the fallback logic.
Quoted 7 lines
Also the kernel feature detection logic should be separated from the exclude bit tests since it depends on the PMU implementation rather than the core kernel features. So I changed it to use a software event for the detection and factor out some hw-specific checks.
The code is available at 'perf/exclude-v4' branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git
Apart from few minor things, series looks good to me:
Thanks,
Ravi