linux/tools/perf/tests/event_groups.c

158 lines
4.2 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
#include <string.h>
#include <unistd.h>
#include <stdio.h>
#include "linux/perf_event.h"
#include "tests.h"
#include "debug.h"
#include "pmu.h"
#include "pmus.h"
#include "header.h"
#include "../perf-sys.h"
perf test: Update event_groups test to use instructions In some of the powerpc platforms, event group testcase fails as below: # perf test -v 'Event groups' 69: Event groups : --- start --- test child forked, pid 9765 Using CPUID 0x00820200 Using hv_24x7 for uncore pmu event 0x0 0x0, 0x0 0x0, 0x0 0x0: Fail 0x0 0x0, 0x0 0x0, 0x1 0x3: Pass The testcase creates various combinations of hw, sw and uncore PMU events and verify group creation succeeds or fails as expected. This tests one of the limitation in perf where it doesn't allow creating a group of events from different hw PMUs. The testcase starts a leader event and opens two sibling events. The combination the fails is three hardware events in a group. "0x0 0x0, 0x0 0x0, 0x0 0x0: Fail" Type zero and config zero which translates to PERF_TYPE_HARDWARE and PERF_COUNT_HW_CPU_CYCLE. There is event constraint in powerpc that events using same counter cannot be programmed in a group. Here there is one alternative event for cycles, hence one leader and only one sibling event can go in as a group. if all three events (leader and two sibling events), are hardware events, use instructions as one of the sibling event. Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware event and present in all architectures, use this as third event. Reported-by: Tejas Manhas <Tejas.Manhas1@ibm.com> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Link: https://lore.kernel.org/r/20250110094620.94976-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-01-10 15:16:20 +05:30
/* hw: cycles,instructions sw: context-switch, uncore: [arch dependent] */
static int types[] = {0, 1, -1};
static unsigned long configs[] = {0, 3, 0};
perf test: Update event_groups test to use instructions In some of the powerpc platforms, event group testcase fails as below: # perf test -v 'Event groups' 69: Event groups : --- start --- test child forked, pid 9765 Using CPUID 0x00820200 Using hv_24x7 for uncore pmu event 0x0 0x0, 0x0 0x0, 0x0 0x0: Fail 0x0 0x0, 0x0 0x0, 0x1 0x3: Pass The testcase creates various combinations of hw, sw and uncore PMU events and verify group creation succeeds or fails as expected. This tests one of the limitation in perf where it doesn't allow creating a group of events from different hw PMUs. The testcase starts a leader event and opens two sibling events. The combination the fails is three hardware events in a group. "0x0 0x0, 0x0 0x0, 0x0 0x0: Fail" Type zero and config zero which translates to PERF_TYPE_HARDWARE and PERF_COUNT_HW_CPU_CYCLE. There is event constraint in powerpc that events using same counter cannot be programmed in a group. Here there is one alternative event for cycles, hence one leader and only one sibling event can go in as a group. if all three events (leader and two sibling events), are hardware events, use instructions as one of the sibling event. Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware event and present in all architectures, use this as third event. Reported-by: Tejas Manhas <Tejas.Manhas1@ibm.com> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Link: https://lore.kernel.org/r/20250110094620.94976-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-01-10 15:16:20 +05:30
static unsigned long configs_hw[] = {1};
#define NR_UNCORE_PMUS 5
/* Uncore pmus that support more than 3 counters */
static struct uncore_pmus {
const char *name;
__u64 config;
} uncore_pmus[NR_UNCORE_PMUS] = {
{ "amd_l3", 0x0 },
{ "amd_df", 0x0 },
{ "uncore_imc_0", 0x1 }, /* Intel */
{ "core_imc", 0x318 }, /* PowerPC: core_imc/CPM_STCX_FIN/ */
{ "hv_24x7", 0x22000000003 }, /* PowerPC: hv_24x7/CPM_STCX_FIN/ */
};
static int event_open(int type, unsigned long config, int group_fd)
{
struct perf_event_attr attr;
memset(&attr, 0, sizeof(struct perf_event_attr));
attr.type = type;
attr.size = sizeof(struct perf_event_attr);
attr.config = config;
/*
* When creating an event group, typically the group leader is
* initialized with disabled set to 1 and any child events are
* initialized with disabled set to 0. Despite disabled being 0,
* the child events will not start until the group leader is
* enabled.
*/
attr.disabled = group_fd == -1 ? 1 : 0;
return sys_perf_event_open(&attr, -1, 0, group_fd, 0);
}
static int setup_uncore_event(void)
{
perf pmus: Prefer perf_pmu__scan over perf_pmus__for_each_pmu perf_pmus__for_each_pmu doesn't lazily initialize pmus making its use error prone. Just use perf_pmu__scan as this only impacts non-performance critical tests. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-26-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:01 -07:00
struct perf_pmu *pmu = NULL;
int i, fd;
perf pmu: Separate pmu and pmus Separate and hide the pmus list in pmus.[ch]. Move pmus functionality out of pmu.[ch] into pmus.[ch] renaming pmus functions which were prefixed perf_pmu__ to perf_pmus__. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-28-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:03 -07:00
while ((pmu = perf_pmus__scan(pmu)) != NULL) {
for (i = 0; i < NR_UNCORE_PMUS; i++) {
if (!strcmp(uncore_pmus[i].name, pmu->name)) {
pr_debug("Using %s for uncore pmu event\n", pmu->name);
types[2] = pmu->type;
configs[2] = uncore_pmus[i].config;
/*
* Check if the chosen uncore pmu event can be
* used in the test. For example, incase of accessing
* hv_24x7 pmu counters, partition should have
* additional permissions. If not, event open will
* fail. So check if the event open succeeds
* before proceeding.
*/
fd = event_open(types[2], configs[2], -1);
if (fd < 0)
return -1;
close(fd);
return 0;
}
}
}
return -1;
}
static int run_test(int i, int j, int k)
{
int erroneous = ((((1 << i) | (1 << j) | (1 << k)) & 5) == 5);
int group_fd, sibling_fd1, sibling_fd2;
group_fd = event_open(types[i], configs[i], -1);
if (group_fd == -1)
return -1;
sibling_fd1 = event_open(types[j], configs[j], group_fd);
if (sibling_fd1 == -1) {
close(group_fd);
return erroneous ? 0 : -1;
}
perf test: Update event_groups test to use instructions In some of the powerpc platforms, event group testcase fails as below: # perf test -v 'Event groups' 69: Event groups : --- start --- test child forked, pid 9765 Using CPUID 0x00820200 Using hv_24x7 for uncore pmu event 0x0 0x0, 0x0 0x0, 0x0 0x0: Fail 0x0 0x0, 0x0 0x0, 0x1 0x3: Pass The testcase creates various combinations of hw, sw and uncore PMU events and verify group creation succeeds or fails as expected. This tests one of the limitation in perf where it doesn't allow creating a group of events from different hw PMUs. The testcase starts a leader event and opens two sibling events. The combination the fails is three hardware events in a group. "0x0 0x0, 0x0 0x0, 0x0 0x0: Fail" Type zero and config zero which translates to PERF_TYPE_HARDWARE and PERF_COUNT_HW_CPU_CYCLE. There is event constraint in powerpc that events using same counter cannot be programmed in a group. Here there is one alternative event for cycles, hence one leader and only one sibling event can go in as a group. if all three events (leader and two sibling events), are hardware events, use instructions as one of the sibling event. Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware event and present in all architectures, use this as third event. Reported-by: Tejas Manhas <Tejas.Manhas1@ibm.com> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Link: https://lore.kernel.org/r/20250110094620.94976-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-01-10 15:16:20 +05:30
/*
* if all three events (leader and two sibling events)
* are hardware events, use instructions as one of the
* sibling event. There is event constraint in powerpc that
* events using same counter cannot be programmed in a group.
* Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware
* event and present in all platforms, lets use that.
*/
if (!i && !j && !k)
sibling_fd2 = event_open(types[k], configs_hw[k], group_fd);
else
sibling_fd2 = event_open(types[k], configs[k], group_fd);
if (sibling_fd2 == -1) {
close(sibling_fd1);
close(group_fd);
return erroneous ? 0 : -1;
}
close(sibling_fd2);
close(sibling_fd1);
close(group_fd);
return erroneous ? -1 : 0;
}
static int test__event_groups(struct test_suite *text __maybe_unused, int subtest __maybe_unused)
{
int i, j, k;
int ret;
int r;
ret = setup_uncore_event();
if (ret || types[2] == -1)
return TEST_SKIP;
ret = TEST_OK;
for (i = 0; i < 3; i++) {
for (j = 0; j < 3; j++) {
for (k = 0; k < 3; k++) {
r = run_test(i, j, k);
if (r)
ret = TEST_FAIL;
perf test: Update event_groups test to use instructions In some of the powerpc platforms, event group testcase fails as below: # perf test -v 'Event groups' 69: Event groups : --- start --- test child forked, pid 9765 Using CPUID 0x00820200 Using hv_24x7 for uncore pmu event 0x0 0x0, 0x0 0x0, 0x0 0x0: Fail 0x0 0x0, 0x0 0x0, 0x1 0x3: Pass The testcase creates various combinations of hw, sw and uncore PMU events and verify group creation succeeds or fails as expected. This tests one of the limitation in perf where it doesn't allow creating a group of events from different hw PMUs. The testcase starts a leader event and opens two sibling events. The combination the fails is three hardware events in a group. "0x0 0x0, 0x0 0x0, 0x0 0x0: Fail" Type zero and config zero which translates to PERF_TYPE_HARDWARE and PERF_COUNT_HW_CPU_CYCLE. There is event constraint in powerpc that events using same counter cannot be programmed in a group. Here there is one alternative event for cycles, hence one leader and only one sibling event can go in as a group. if all three events (leader and two sibling events), are hardware events, use instructions as one of the sibling event. Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware event and present in all architectures, use this as third event. Reported-by: Tejas Manhas <Tejas.Manhas1@ibm.com> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Link: https://lore.kernel.org/r/20250110094620.94976-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-01-10 15:16:20 +05:30
/*
* For all three events as HW events, second sibling
* event is picked from configs_hw. So print accordingly
*/
if (!i && !j && !k)
pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n",
types[i], configs[i], types[j], configs[j],
types[k], configs_hw[k], r ? "Fail" : "Pass");
else
pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n",
types[i], configs[i], types[j], configs[j],
types[k], configs[k], r ? "Fail" : "Pass");
}
}
}
return ret;
}
DEFINE_SUITE("Event groups", event_groups);