summaryrefslogtreecommitdiffstats
path: root/tools/perf/arch
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/arch')
-rw-r--r--tools/perf/arch/arm/util/cs-etm.c1
-rw-r--r--tools/perf/arch/arm64/util/arm-spe.c1
-rw-r--r--tools/perf/arch/arm64/util/perf_regs.c38
-rw-r--r--tools/perf/arch/arm64/util/unwind-libunwind.c73
-rw-r--r--tools/perf/arch/riscv/Makefile1
-rw-r--r--tools/perf/arch/s390/util/auxtrace.c1
-rw-r--r--tools/perf/arch/x86/util/evlist.c7
-rw-r--r--tools/perf/arch/x86/util/evsel.c31
-rw-r--r--tools/perf/arch/x86/util/intel-bts.c1
-rw-r--r--tools/perf/arch/x86/util/intel-pt.c32
-rw-r--r--tools/perf/arch/x86/util/topdown.c25
-rw-r--r--tools/perf/arch/x86/util/topdown.h7
12 files changed, 126 insertions, 92 deletions
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 11c71aa219f7..1b54638d53b0 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -319,6 +319,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
}
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
+ evsel->needs_auxtrace_mmap = true;
cs_etm_evsel = evsel;
opts->full_auxtrace = true;
}
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index e8b577d33e53..6f4db2ac5420 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -160,6 +160,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
}
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period;
+ evsel->needs_auxtrace_mmap = true;
arm_spe_evsel = evsel;
opts->full_auxtrace = true;
}
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 476b037eea1c..006692c9b040 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -2,13 +2,19 @@
#include <errno.h>
#include <regex.h>
#include <string.h>
+#include <sys/auxv.h>
#include <linux/kernel.h>
#include <linux/zalloc.h>
+#include "../../../perf-sys.h"
#include "../../../util/debug.h"
#include "../../../util/event.h"
#include "../../../util/perf_regs.h"
+#ifndef HWCAP_SVE
+#define HWCAP_SVE (1 << 22)
+#endif
+
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(x0, PERF_REG_ARM64_X0),
SMPL_REG(x1, PERF_REG_ARM64_X1),
@@ -43,6 +49,7 @@ const struct sample_reg sample_reg_masks[] = {
SMPL_REG(lr, PERF_REG_ARM64_LR),
SMPL_REG(sp, PERF_REG_ARM64_SP),
SMPL_REG(pc, PERF_REG_ARM64_PC),
+ SMPL_REG(vg, PERF_REG_ARM64_VG),
SMPL_REG_END
};
@@ -131,3 +138,34 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
return SDT_ARG_VALID;
}
+
+uint64_t arch__user_reg_mask(void)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .sample_type = PERF_SAMPLE_REGS_USER,
+ .disabled = 1,
+ .exclude_kernel = 1,
+ .sample_period = 1,
+ .sample_regs_user = PERF_REGS_MASK
+ };
+ int fd;
+
+ if (getauxval(AT_HWCAP) & HWCAP_SVE)
+ attr.sample_regs_user |= SMPL_REG_MASK(PERF_REG_ARM64_VG);
+
+ /*
+ * Check if the pmu supports perf extended regs, before
+ * returning the register mask to sample.
+ */
+ if (attr.sample_regs_user != PERF_REGS_MASK) {
+ event_attr_init(&attr);
+ fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+ if (fd != -1) {
+ close(fd);
+ return attr.sample_regs_user;
+ }
+ }
+ return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 5aecf88e3de6..871af5992298 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -10,77 +10,8 @@
int LIBUNWIND__ARCH_REG_ID(int regnum)
{
- switch (regnum) {
- case UNW_AARCH64_X0:
- return PERF_REG_ARM64_X0;
- case UNW_AARCH64_X1:
- return PERF_REG_ARM64_X1;
- case UNW_AARCH64_X2:
- return PERF_REG_ARM64_X2;
- case UNW_AARCH64_X3:
- return PERF_REG_ARM64_X3;
- case UNW_AARCH64_X4:
- return PERF_REG_ARM64_X4;
- case UNW_AARCH64_X5:
- return PERF_REG_ARM64_X5;
- case UNW_AARCH64_X6:
- return PERF_REG_ARM64_X6;
- case UNW_AARCH64_X7:
- return PERF_REG_ARM64_X7;
- case UNW_AARCH64_X8:
- return PERF_REG_ARM64_X8;
- case UNW_AARCH64_X9:
- return PERF_REG_ARM64_X9;
- case UNW_AARCH64_X10:
- return PERF_REG_ARM64_X10;
- case UNW_AARCH64_X11:
- return PERF_REG_ARM64_X11;
- case UNW_AARCH64_X12:
- return PERF_REG_ARM64_X12;
- case UNW_AARCH64_X13:
- return PERF_REG_ARM64_X13;
- case UNW_AARCH64_X14:
- return PERF_REG_ARM64_X14;
- case UNW_AARCH64_X15:
- return PERF_REG_ARM64_X15;
- case UNW_AARCH64_X16:
- return PERF_REG_ARM64_X16;
- case UNW_AARCH64_X17:
- return PERF_REG_ARM64_X17;
- case UNW_AARCH64_X18:
- return PERF_REG_ARM64_X18;
- case UNW_AARCH64_X19:
- return PERF_REG_ARM64_X19;
- case UNW_AARCH64_X20:
- return PERF_REG_ARM64_X20;
- case UNW_AARCH64_X21:
- return PERF_REG_ARM64_X21;
- case UNW_AARCH64_X22:
- return PERF_REG_ARM64_X22;
- case UNW_AARCH64_X23:
- return PERF_REG_ARM64_X23;
- case UNW_AARCH64_X24:
- return PERF_REG_ARM64_X24;
- case UNW_AARCH64_X25:
- return PERF_REG_ARM64_X25;
- case UNW_AARCH64_X26:
- return PERF_REG_ARM64_X26;
- case UNW_AARCH64_X27:
- return PERF_REG_ARM64_X27;
- case UNW_AARCH64_X28:
- return PERF_REG_ARM64_X28;
- case UNW_AARCH64_X29:
- return PERF_REG_ARM64_X29;
- case UNW_AARCH64_X30:
- return PERF_REG_ARM64_LR;
- case UNW_AARCH64_SP:
- return PERF_REG_ARM64_SP;
- case UNW_AARCH64_PC:
- return PERF_REG_ARM64_PC;
- default:
- pr_err("unwind: invalid reg id %d\n", regnum);
+ if (regnum < 0 || regnum >= PERF_REG_ARM64_EXTENDED_MAX)
return -EINVAL;
- }
- return -EINVAL;
+ return regnum;
}
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
index 1aa9dd772489..a8d25d005207 100644
--- a/tools/perf/arch/riscv/Makefile
+++ b/tools/perf/arch/riscv/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index 0db5c58c98e8..5068baa3e092 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -98,6 +98,7 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
evlist__for_each_entry(evlist, pos) {
if (pos->core.attr.config == PERF_EVENT_CPUM_SF_DIAG) {
diagnose = 1;
+ pos->needs_auxtrace_mmap = true;
break;
}
}
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index cfc208d71f00..68f681ad54c1 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -3,6 +3,7 @@
#include "util/pmu.h"
#include "util/evlist.h"
#include "util/parse-events.h"
+#include "topdown.h"
#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
#define TOPDOWN_L2_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
@@ -25,18 +26,18 @@ struct evsel *arch_evlist__leader(struct list_head *list)
first = list_first_entry(list, struct evsel, core.node);
- if (!pmu_have_event("cpu", "slots"))
+ if (!topdown_sys_has_perf_metrics())
return first;
/* If there is a slots event and a topdown event then the slots event comes first. */
__evlist__for_each_entry(list, evsel) {
- if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
+ if (evsel->pmu_name && !strncmp(evsel->pmu_name, "cpu", 3) && evsel->name) {
if (strcasestr(evsel->name, "slots")) {
slots = evsel;
if (slots == first)
return first;
}
- if (!strncasecmp(evsel->name, "topdown", 7))
+ if (strcasestr(evsel->name, "topdown"))
has_topdown = true;
if (slots && has_topdown)
return slots;
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ac2899a25b7a..88306183d629 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -3,6 +3,7 @@
#include <stdlib.h>
#include "util/evsel.h"
#include "util/env.h"
+#include "util/pmu.h"
#include "linux/string.h"
void arch_evsel__set_sample_weight(struct evsel *evsel)
@@ -29,3 +30,33 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
free(env.cpuid);
}
+
+/* Check whether the evsel's PMU supports the perf metrics */
+static bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
+{
+ const char *pmu_name = evsel->pmu_name ? evsel->pmu_name : "cpu";
+
+ /*
+ * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU
+ * on a non-hybrid machine, "cpu_core" PMU on a hybrid machine.
+ * The slots event is only available for the core PMU, which
+ * supports the perf metrics feature.
+ * Checking both the PERF_TYPE_RAW type and the slots event
+ * should be good enough to detect the perf metrics feature.
+ */
+ if ((evsel->core.attr.type == PERF_TYPE_RAW) &&
+ pmu_have_event(pmu_name, "slots"))
+ return true;
+
+ return false;
+}
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel)
+{
+ if (!evsel__sys_has_perf_metrics(evsel))
+ return false;
+
+ return evsel->name &&
+ (!strcasecmp(evsel->name, "slots") ||
+ strcasestr(evsel->name, "topdown"));
+}
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index d68a0f48e41e..bcccfbade5c6 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -129,6 +129,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
}
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
+ evsel->needs_auxtrace_mmap = true;
intel_bts_evsel = evsel;
opts->full_auxtrace = true;
}
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 38ec2666ec12..06c2cdfd8f2f 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -649,6 +649,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
evsel->no_aux_samples = true;
+ evsel->needs_auxtrace_mmap = true;
intel_pt_evsel = evsel;
opts->full_auxtrace = true;
}
@@ -810,18 +811,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
if (!cpu_wide && perf_can_record_cpu_wide()) {
struct evsel *switch_evsel;
- err = parse_events(evlist, "dummy:u", NULL);
- if (err)
- return err;
+ switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
+ if (!switch_evsel)
+ return -ENOMEM;
- switch_evsel = evlist__last(evlist);
-
- switch_evsel->core.attr.freq = 0;
- switch_evsel->core.attr.sample_period = 1;
switch_evsel->core.attr.context_switch = 1;
-
- switch_evsel->core.system_wide = true;
- switch_evsel->no_aux_samples = true;
switch_evsel->immediate = true;
evsel__set_sample_bit(switch_evsel, TID);
@@ -870,20 +864,22 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
/* Add dummy event to keep tracking */
if (opts->full_auxtrace) {
+ bool need_system_wide_tracking;
struct evsel *tracking_evsel;
- err = parse_events(evlist, "dummy:u", NULL);
- if (err)
- return err;
+ /*
+ * User space tasks can migrate between CPUs, so when tracing
+ * selected CPUs, sideband for all CPUs is still needed.
+ */
+ need_system_wide_tracking = evlist->core.has_user_cpus &&
+ !intel_pt_evsel->core.attr.exclude_user;
- tracking_evsel = evlist__last(evlist);
+ tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking);
+ if (!tracking_evsel)
+ return -ENOMEM;
evlist__set_tracking_event(evlist, tracking_evsel);
- tracking_evsel->core.attr.freq = 0;
- tracking_evsel->core.attr.sample_period = 1;
-
- tracking_evsel->no_aux_samples = true;
if (need_immediate)
tracking_evsel->immediate = true;
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index 2f3d96aa92a5..f4d5422e9960 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -3,6 +3,31 @@
#include "api/fs/fs.h"
#include "util/pmu.h"
#include "util/topdown.h"
+#include "topdown.h"
+
+/* Check whether there is a PMU which supports the perf metrics. */
+bool topdown_sys_has_perf_metrics(void)
+{
+ static bool has_perf_metrics;
+ static bool cached;
+ struct perf_pmu *pmu;
+
+ if (cached)
+ return has_perf_metrics;
+
+ /*
+ * The perf metrics feature is a core PMU feature.
+ * The PERF_TYPE_RAW type is the type of a core PMU.
+ * The slots event is only available when the core PMU
+ * supports the perf metrics feature.
+ */
+ pmu = perf_pmu__find_by_type(PERF_TYPE_RAW);
+ if (pmu && pmu_have_event(pmu->name, "slots"))
+ has_perf_metrics = true;
+
+ cached = true;
+ return has_perf_metrics;
+}
/*
* Check whether we can use a group for top down.
diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
new file mode 100644
index 000000000000..46bf9273e572
--- /dev/null
+++ b/tools/perf/arch/x86/util/topdown.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOPDOWN_H
+#define _TOPDOWN_H 1
+
+bool topdown_sys_has_perf_metrics(void);
+
+#endif
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-08 13:49:15 +0000