aboutsummaryrefslogtreecommitdiffstats
path: root/tools/perf/arch/x86/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/arch/x86/util')
-rw-r--r--tools/perf/arch/x86/util/Build6
-rw-r--r--tools/perf/arch/x86/util/archinsn.c11
-rw-r--r--tools/perf/arch/x86/util/cpuid.h34
-rw-r--r--tools/perf/arch/x86/util/event.c27
-rw-r--r--tools/perf/arch/x86/util/evlist.c93
-rw-r--r--tools/perf/arch/x86/util/evsel.c135
-rw-r--r--tools/perf/arch/x86/util/evsel.h7
-rw-r--r--tools/perf/arch/x86/util/group.c28
-rw-r--r--tools/perf/arch/x86/util/header.c27
-rw-r--r--tools/perf/arch/x86/util/intel-bts.c11
-rw-r--r--tools/perf/arch/x86/util/intel-pt.c133
-rw-r--r--tools/perf/arch/x86/util/iostat.c470
-rw-r--r--tools/perf/arch/x86/util/kvm-stat.c58
-rw-r--r--tools/perf/arch/x86/util/mem-events.c107
-rw-r--r--tools/perf/arch/x86/util/perf_regs.c16
-rw-r--r--tools/perf/arch/x86/util/pmu.c155
-rw-r--r--tools/perf/arch/x86/util/topdown.c126
-rw-r--r--tools/perf/arch/x86/util/topdown.h8
-rw-r--r--tools/perf/arch/x86/util/tsc.c130
-rw-r--r--tools/perf/arch/x86/util/unwind-libdw.c6
20 files changed, 1401 insertions, 187 deletions
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 47f9c56e744f..dbeb04cb336e 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -3,9 +3,13 @@ perf-y += tsc.o
perf-y += pmu.o
perf-y += kvm-stat.o
perf-y += perf_regs.o
-perf-y += group.o
+perf-y += topdown.o
perf-y += machine.o
perf-y += event.o
+perf-y += evlist.o
+perf-y += mem-events.o
+perf-y += evsel.o
+perf-y += iostat.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 3e6791531ca5..546feda08428 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -1,17 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
-#include "../../../../arch/x86/include/asm/insn.h"
#include "archinsn.h"
#include "event.h"
#include "machine.h"
#include "thread.h"
#include "symbol.h"
+#include "../../../../arch/x86/include/asm/insn.h"
void arch_fetch_insn(struct perf_sample *sample,
struct thread *thread,
struct machine *machine)
{
struct insn insn;
- int len;
+ int len, ret;
bool is64bit = false;
if (!sample->ip)
@@ -19,8 +19,9 @@ void arch_fetch_insn(struct perf_sample *sample,
len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
if (len <= 0)
return;
- insn_init(&insn, sample->insn, len, is64bit);
- insn_get_length(&insn);
- if (insn_complete(&insn) && insn.length <= len)
+
+ ret = insn_decode(&insn, sample->insn, len,
+ is64bit ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret >= 0 && insn.length <= len)
sample->insn_len = insn.length;
}
diff --git a/tools/perf/arch/x86/util/cpuid.h b/tools/perf/arch/x86/util/cpuid.h
new file mode 100644
index 000000000000..0a3ae0ace7e9
--- /dev/null
+++ b/tools/perf/arch/x86/util/cpuid.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CPUID_H
+#define PERF_CPUID_H 1
+
+
+static inline void
+cpuid(unsigned int op, unsigned int op2, unsigned int *a, unsigned int *b,
+ unsigned int *c, unsigned int *d)
+{
+ /*
+ * Preserve %ebx/%rbx register by either placing it in %rdi or saving it
+ * on the stack - x86-64 needs to avoid the stack red zone. In PIC
+ * compilations %ebx contains the address of the global offset
+ * table. %rbx is occasionally used to address stack variables in
+ * presence of dynamic allocas.
+ */
+ asm(
+#if defined(__x86_64__)
+ "mov %%rbx, %%rdi\n"
+ "cpuid\n"
+ "xchg %%rdi, %%rbx\n"
+#else
+ "pushl %%ebx\n"
+ "cpuid\n"
+ "movl %%ebx, %%edi\n"
+ "popl %%ebx\n"
+#endif
+ : "=a"(*a), "=D"(*b), "=c"(*c), "=d"(*d)
+ : "a"(op), "2"(op2));
+}
+
+void get_cpuid_0(char *vendor, unsigned int *lvl);
+
+#endif
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index 047dc00eafa6..e670f3547581 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -18,7 +18,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
{
int rc = 0;
struct map *pos;
- struct maps *kmaps = &machine->kmaps;
+ struct maps *kmaps = machine__kernel_maps(machine);
union perf_event *event = zalloc(sizeof(event->mmap) +
machine->id_hdr_size);
@@ -75,3 +75,28 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
}
#endif
+
+void arch_perf_parse_sample_weight(struct perf_sample *data,
+ const __u64 *array, u64 type)
+{
+ union perf_sample_weight weight;
+
+ weight.full = *array;
+ if (type & PERF_SAMPLE_WEIGHT)
+ data->weight = weight.full;
+ else {
+ data->weight = weight.var1_dw;
+ data->ins_lat = weight.var2_w;
+ }
+}
+
+void arch_perf_synthesize_sample_weight(const struct perf_sample *data,
+ __u64 *array, u64 type)
+{
+ *array = data->weight;
+
+ if (type & PERF_SAMPLE_WEIGHT_STRUCT) {
+ *array &= 0xffffffff;
+ *array |= ((u64)data->ins_lat << 32);
+ }
+}
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
new file mode 100644
index 000000000000..cb59ce9b9638
--- /dev/null
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "util/pmu.h"
+#include "util/evlist.h"
+#include "util/parse-events.h"
+#include "util/event.h"
+#include "util/pmu-hybrid.h"
+#include "topdown.h"
+
+static int ___evlist__add_default_attrs(struct evlist *evlist,
+ struct perf_event_attr *attrs,
+ size_t nr_attrs)
+{
+ struct perf_cpu_map *cpus;
+ struct evsel *evsel, *n;
+ struct perf_pmu *pmu;
+ LIST_HEAD(head);
+ size_t i = 0;
+
+ for (i = 0; i < nr_attrs; i++)
+ event_attr_init(attrs + i);
+
+ if (!perf_pmu__has_hybrid())
+ return evlist__add_attrs(evlist, attrs, nr_attrs);
+
+ for (i = 0; i < nr_attrs; i++) {
+ if (attrs[i].type == PERF_TYPE_SOFTWARE) {
+ evsel = evsel__new(attrs + i);
+ if (evsel == NULL)
+ goto out_delete_partial_list;
+ list_add_tail(&evsel->core.node, &head);
+ continue;
+ }
+
+ perf_pmu__for_each_hybrid_pmu(pmu) {
+ evsel = evsel__new(attrs + i);
+ if (evsel == NULL)
+ goto out_delete_partial_list;
+ evsel->core.attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+ cpus = perf_cpu_map__get(pmu->cpus);
+ evsel->core.cpus = cpus;
+ evsel->core.own_cpus = perf_cpu_map__get(cpus);
+ evsel->pmu_name = strdup(pmu->name);
+ list_add_tail(&evsel->core.node, &head);
+ }
+ }
+
+ evlist__splice_list_tail(evlist, &head);
+
+ return 0;
+
+out_delete_partial_list:
+ __evlist__for_each_entry_safe(&head, n, evsel)
+ evsel__delete(evsel);
+ return -1;
+}
+
+int arch_evlist__add_default_attrs(struct evlist *evlist,
+ struct perf_event_attr *attrs,
+ size_t nr_attrs)
+{
+ if (nr_attrs)
+ return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
+
+ return topdown_parse_events(evlist);
+}
+
+struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ struct evsel *evsel, *first, *slots = NULL;
+ bool has_topdown = false;
+
+ first = list_first_entry(list, struct evsel, core.node);
+
+ 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 && !strncmp(evsel->pmu_name, "cpu", 3) && evsel->name) {
+ if (strcasestr(evsel->name, "slots")) {
+ slots = evsel;
+ if (slots == first)
+ return first;
+ }
+ if (strcasestr(evsel->name, "topdown"))
+ has_topdown = true;
+ if (slots && has_topdown)
+ return slots;
+ }
+ }
+ return first;
+}
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
new file mode 100644
index 000000000000..ea3972d785d1
--- /dev/null
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include "util/evsel.h"
+#include "util/env.h"
+#include "util/pmu.h"
+#include "linux/string.h"
+#include "evsel.h"
+#include "util/debug.h"
+
+#define IBS_FETCH_L3MISSONLY (1ULL << 59)
+#define IBS_OP_L3MISSONLY (1ULL << 16)
+
+void arch_evsel__set_sample_weight(struct evsel *evsel)
+{
+ evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
+}
+
+void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
+{
+ struct perf_env env = { .total_mem = 0, } ;
+
+ if (!perf_env__cpuid(&env))
+ return;
+
+ /*
+ * On AMD, precise cycles event sampling internally uses IBS pmu.
+ * But IBS does not have filtering capabilities and perf by default
+ * sets exclude_guest = 1. This makes IBS pmu event init fail and
+ * thus perf ends up doing non-precise sampling. Avoid it by clearing
+ * exclude_guest.
+ */
+ if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
+ attr->exclude_guest = 0;
+
+ free(env.cpuid);
+}
+
+/* Check whether the evsel's PMU supports the perf metrics */
+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 &&
+ (strcasestr(evsel->name, "slots") ||
+ strcasestr(evsel->name, "topdown"));
+}
+
+int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+{
+ u64 event = evsel->core.attr.config & PERF_HW_EVENT_MASK;
+ u64 pmu = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+ const char *event_name;
+
+ if (event < PERF_COUNT_HW_MAX && evsel__hw_names[event])
+ event_name = evsel__hw_names[event];
+ else
+ event_name = "unknown-hardware";
+
+ /* The PMU type is not required for the non-hybrid platform. */
+ if (!pmu)
+ return scnprintf(bf, size, "%s", event_name);
+
+ return scnprintf(bf, size, "%s/%s/",
+ evsel->pmu_name ? evsel->pmu_name : "cpu",
+ event_name);
+}
+
+static void ibs_l3miss_warn(void)
+{
+ pr_warning(
+"WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled\n"
+"and tagged operation does not cause L3 Miss. This causes sampling period skew.\n");
+}
+
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
+{
+ struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
+ static int warned_once;
+ /* 0: Uninitialized, 1: Yes, -1: No */
+ static int is_amd;
+
+ if (warned_once || is_amd == -1)
+ return;
+
+ if (!is_amd) {
+ struct perf_env *env = evsel__env(evsel);
+
+ if (!perf_env__cpuid(env) || !env->cpuid ||
+ !strstarts(env->cpuid, "AuthenticAMD")) {
+ is_amd = -1;
+ return;
+ }
+ is_amd = 1;
+ }
+
+ evsel_pmu = evsel__find_pmu(evsel);
+ if (!evsel_pmu)
+ return;
+
+ ibs_fetch_pmu = perf_pmu__find("ibs_fetch");
+ ibs_op_pmu = perf_pmu__find("ibs_op");
+
+ if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
+ if (attr->config & IBS_FETCH_L3MISSONLY) {
+ ibs_l3miss_warn();
+ warned_once = 1;
+ }
+ } else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+ if (attr->config & IBS_OP_L3MISSONLY) {
+ ibs_l3miss_warn();
+ warned_once = 1;
+ }
+ }
+}
diff --git a/tools/perf/arch/x86/util/evsel.h b/tools/perf/arch/x86/util/evsel.h
new file mode 100644
index 000000000000..19ad1691374d
--- /dev/null
+++ b/tools/perf/arch/x86/util/evsel.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EVSEL_H
+#define _EVSEL_H 1
+
+bool evsel__sys_has_perf_metrics(const struct evsel *evsel);
+
+#endif
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
deleted file mode 100644
index e2f8034b8973..000000000000
--- a/tools/perf/arch/x86/util/group.c
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include "api/fs/fs.h"
-#include "util/group.h"
-
-/*
- * Check whether we can use a group for top down.
- * Without a group may get bad results due to multiplexing.
- */
-bool arch_topdown_check_group(bool *warn)
-{
- int n;
-
- if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
- return false;
- if (n > 0) {
- *warn = true;
- return false;
- }
- return true;
-}
-
-void arch_topdown_group_warn(void)
-{
- fprintf(stderr,
- "nmi_watchdog enabled with topdown. May give wrong results.\n"
- "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
-}
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 578c8c568ffd..a51444a77a5f 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -9,18 +9,17 @@
#include "../../../util/debug.h"
#include "../../../util/header.h"
+#include "cpuid.h"
-static inline void
-cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
- unsigned int *d)
+void get_cpuid_0(char *vendor, unsigned int *lvl)
{
- __asm__ __volatile__ (".byte 0x53\n\tcpuid\n\t"
- "movl %%ebx, %%esi\n\t.byte 0x5b"
- : "=a" (*a),
- "=S" (*b),
- "=c" (*c),
- "=d" (*d)
- : "a" (op));
+ unsigned int b, c, d;
+
+ cpuid(0, 0, lvl, &b, &c, &d);
+ strncpy(&vendor[0], (char *)(&b), 4);
+ strncpy(&vendor[4], (char *)(&d), 4);
+ strncpy(&vendor[8], (char *)(&c), 4);
+ vendor[12] = '\0';
}
static int
@@ -31,14 +30,10 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
int nb;
char vendor[16];
- cpuid(0, &lvl, &b, &c, &d);
- strncpy(&vendor[0], (char *)(&b), 4);
- strncpy(&vendor[4], (char *)(&d), 4);
- strncpy(&vendor[8], (char *)(&c), 4);
- vendor[12] = '\0';
+ get_cpuid_0(vendor, &lvl);
if (lvl >= 1) {
- cpuid(1, &a, &b, &c, &d);
+ cpuid(1, 0, &a, &b, &c, &d);
family = (a >> 8) & 0xf; /* bits 11 - 8 */
model = (a >> 4) & 0xf; /* Bits 7 - 4 */
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 09f93800bffd..439c2956f3e7 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -110,7 +110,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
container_of(itr, struct intel_bts_recording, itr);
struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
struct evsel *evsel, *intel_bts_evsel = NULL;
- const struct perf_cpu_map *cpus = evlist->core.cpus;
+ const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
if (opts->auxtrace_sample_mode) {
@@ -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;
}
@@ -218,13 +219,13 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
* To obtain the auxtrace buffer file descriptor, the auxtrace event
* must come first.
*/
- perf_evlist__to_front(evlist, intel_bts_evsel);
+ evlist__to_front(evlist, intel_bts_evsel);
/*
* In the case of per-cpu mmaps, we need the CPU on the
* AUX event.
*/
if (!perf_cpu_map__empty(cpus))
- perf_evsel__set_sample_bit(intel_bts_evsel, CPU);
+ evsel__set_sample_bit(intel_bts_evsel, CPU);
}
/* Add dummy event to keep tracking */
@@ -232,13 +233,13 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
struct evsel *tracking_evsel;
int err;
- err = parse_events(evlist, "dummy:u", NULL);
+ err = parse_event(evlist, "dummy:u");
if (err)
return err;
tracking_evsel = evlist__last(evlist);
- perf_evlist__set_tracking_event(evlist, tracking_evsel);
+ evlist__set_tracking_event(evlist, tracking_evsel);
tracking_evsel->core.attr.freq = 0;
tracking_evsel->core.attr.sample_period = 1;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 1643aed8c4c8..af102f471e9f 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -11,6 +11,7 @@
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/zalloc.h>
+#include <linux/err.h>
#include <cpuid.h>
#include "../../../util/session.h"
@@ -25,6 +26,7 @@
#include "../../../util/pmu.h"
#include "../../../util/debug.h"
#include "../../../util/auxtrace.h"
+#include "../../../util/perf_api_probe.h"
#include "../../../util/record.h"
#include "../../../util/target.h"
#include "../../../util/tsc.h"
@@ -58,7 +60,8 @@ struct intel_pt_recording {
size_t priv_size;
};
-static int intel_pt_parse_terms_with_default(struct list_head *formats,
+static int intel_pt_parse_terms_with_default(const char *pmu_name,
+ struct list_head *formats,
const char *str,
u64 *config)
{
@@ -77,7 +80,8 @@ static int intel_pt_parse_terms_with_default(struct list_head *formats,
goto out_free;
attr.config = *config;
- err = perf_pmu__config_terms(formats, &attr, terms, true, NULL);
+ err = perf_pmu__config_terms(pmu_name, formats, &attr, terms, true,
+ NULL);
if (err)
goto out_free;
@@ -87,11 +91,12 @@ out_free:
return err;
}
-static int intel_pt_parse_terms(struct list_head *formats, const char *str,
- u64 *config)
+static int intel_pt_parse_terms(const char *pmu_name, struct list_head *formats,
+ const char *str, u64 *config)
{
*config = 0;
- return intel_pt_parse_terms_with_default(formats, str, config);
+ return intel_pt_parse_terms_with_default(pmu_name, formats, str,
+ config);
}
static u64 intel_pt_masked_bits(u64 mask, u64 bits)
@@ -228,7 +233,8 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf);
- intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config);
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, buf,
+ &config);
return config;
}
@@ -301,6 +307,7 @@ intel_pt_info_priv_size(struct auxtrace_record *itr, struct evlist *evlist)
ptr->priv_size = (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64)) +
intel_pt_filter_bytes(filter);
+ ptr->priv_size += sizeof(u64); /* Cap Event Trace */
return ptr->priv_size;
}
@@ -330,25 +337,32 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
unsigned long max_non_turbo_ratio;
size_t filter_str_len;
const char *filter;
+ int event_trace;
__u64 *info;
int err;
if (priv_size != ptr->priv_size)
return -EINVAL;
- intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
- intel_pt_parse_terms(&intel_pt_pmu->format, "noretcomp",
- &noretcomp_bit);
- intel_pt_parse_terms(&intel_pt_pmu->format, "mtc", &mtc_bit);
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
+ "tsc", &tsc_bit);
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
+ "noretcomp", &noretcomp_bit);
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
+ "mtc", &mtc_bit);
mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format,
"mtc_period");
- intel_pt_parse_terms(&intel_pt_pmu->format, "cyc", &cyc_bit);
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
+ "cyc", &cyc_bit);
intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);
if (perf_pmu__scan_file(intel_pt_pmu, "max_nonturbo_ratio",
"%lu", &max_non_turbo_ratio) != 1)
max_non_turbo_ratio = 0;
+ if (perf_pmu__scan_file(intel_pt_pmu, "caps/event_trace",
+ "%d", &event_trace) != 1)
+ event_trace = 0;
filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu);
filter_str_len = filter ? strlen(filter) : 0;
@@ -369,7 +383,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
ui__warning("Intel Processor Trace: TSC not available\n");
}
- per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus);
+ per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus);
auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -399,6 +413,8 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
info += len >> 3;
}
+ *info++ = event_trace;
+
return 0;
}
@@ -408,23 +424,17 @@ static int intel_pt_track_switches(struct evlist *evlist)
struct evsel *evsel;
int err;
- if (!perf_evlist__can_select_event(evlist, sched_switch))
+ if (!evlist__can_select_event(evlist, sched_switch))
return -EPERM;
- err = parse_events(evlist, sched_switch, NULL);
- if (err) {
- pr_debug2("%s: failed to parse %s, error %d\n",
+ evsel = evlist__add_sched_switch(evlist, true);
+ if (IS_ERR(evsel)) {
+ err = PTR_ERR(evsel);
+ pr_debug2("%s: failed to create %s, error = %d\n",
__func__, sched_switch, err);
return err;
}
- evsel = evlist__last(evlist);
-
- perf_evsel__set_sample_bit(evsel, CPU);
- perf_evsel__set_sample_bit(evsel, TIME);
-
- evsel->core.system_wide = true;
- evsel->no_aux_samples = true;
evsel->immediate = true;
return 0;
@@ -555,10 +565,9 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu,
struct evsel *evsel)
{
- struct perf_evsel_config_term *term;
u64 user_bits = 0, bits;
+ struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG);
- term = perf_evsel__get_config_term(evsel, CFG_CHG);
if (term)
user_bits = term->val.cfg_chg;
@@ -618,7 +627,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
bool have_timing_info, need_immediate = false;
struct evsel *evsel, *intel_pt_evsel = NULL;
- const struct perf_cpu_map *cpus = evlist->core.cpus;
+ const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
u64 tsc_bit;
int err;
@@ -634,6 +643,8 @@ 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;
}
@@ -768,7 +779,14 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
}
}
- intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
+ if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) {
+ u32 aux_watermark = opts->auxtrace_mmap_pages * page_size / 4;
+
+ intel_pt_evsel->core.attr.aux_watermark = aux_watermark;
+ }
+
+ intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
+ "tsc", &tsc_bit);
if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit))
have_timing_info = true;
@@ -779,7 +797,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
* Per-cpu recording needs sched_switch events to distinguish different
* threads.
*/
- if (have_timing_info && !perf_cpu_map__empty(cpus)) {
+ if (have_timing_info && !perf_cpu_map__empty(cpus) &&
+ !record_opts__no_switch_events(opts)) {
if (perf_can_record_switch_events()) {
bool cpu_wide = !target__none(&opts->target) &&
!target__has_task(&opts->target);
@@ -787,24 +806,17 @@ 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__last(evlist);
+ switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
+ if (!switch_evsel)
+ return -ENOMEM;
- 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;
- perf_evsel__set_sample_bit(switch_evsel, TID);
- perf_evsel__set_sample_bit(switch_evsel, TIME);
- perf_evsel__set_sample_bit(switch_evsel, CPU);
- perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
+ evsel__set_sample_bit(switch_evsel, TID);
+ evsel__set_sample_bit(switch_evsel, TIME);
+ evsel__set_sample_bit(switch_evsel, CPU);
+ evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
opts->record_switch_events = false;
ptr->have_sched_switch = 3;
@@ -827,46 +839,52 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
}
}
+ if (have_timing_info && !intel_pt_evsel->core.attr.exclude_kernel &&
+ perf_can_record_text_poke_events() && perf_can_record_cpu_wide())
+ opts->text_poke = true;
+
if (intel_pt_evsel) {
/*
* To obtain the auxtrace buffer file descriptor, the auxtrace
* event must come first.
*/
- perf_evlist__to_front(evlist, intel_pt_evsel);
+ evlist__to_front(evlist, intel_pt_evsel);
/*
* In the case of per-cpu mmaps, we need the CPU on the
* AUX event.
*/
if (!perf_cpu_map__empty(cpus))
- perf_evsel__set_sample_bit(intel_pt_evsel, CPU);
+ evsel__set_sample_bit(intel_pt_evsel, CPU);
}
/* 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;
-
- tracking_evsel = evlist__last(evlist);
+ /*
+ * User space tasks can migrate between CPUs, so when tracing
+ * selected CPUs, sideband for all CPUs is still needed.
+ */
+ need_system_wide_tracking = opts->target.cpu_list &&
+ !intel_pt_evsel->core.attr.exclude_user;
- perf_evlist__set_tracking_event(evlist, tracking_evsel);
+ tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking);
+ if (!tracking_evsel)
+ return -ENOMEM;
- tracking_evsel->core.attr.freq = 0;
- tracking_evsel->core.attr.sample_period = 1;
+ evlist__set_tracking_event(evlist, tracking_evsel);
- tracking_evsel->no_aux_samples = true;
if (need_immediate)
tracking_evsel->immediate = true;
/* In per-cpu case, always need the time of mmap events etc */
if (!perf_cpu_map__empty(cpus)) {
- perf_evsel__set_sample_bit(tracking_evsel, TIME);
+ evsel__set_sample_bit(tracking_evsel, TIME);
/* And the CPU for switch events */
- perf_evsel__set_sample_bit(tracking_evsel, CPU);
+ evsel__set_sample_bit(tracking_evsel, CPU);
}
- perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+ evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
}
/*
@@ -874,7 +892,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
* per-cpu with no sched_switch (except workload-only).
*/
if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) &&
- !target__none(&opts->target))
+ !target__none(&opts->target) &&
+ !intel_pt_evsel->core.attr.exclude_user)
ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
return 0;
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
new file mode 100644
index 000000000000..404de795ec0b
--- /dev/null
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -0,0 +1,470 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * perf iostat
+ *
+ * Copyright (C) 2020, Intel Corporation
+ *
+ * Authors: Alexander Antonov <alexander.antonov@linux.intel.com>
+ */
+
+#include <api/fs/fs.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <regex.h>
+#include "util/cpumap.h"
+#include "util/debug.h"
+#include "util/iostat.h"
+#include "util/counts.h"
+#include "path.h"
+
+#ifndef MAX_PATH
+#define MAX_PATH 1024
+#endif
+
+#define UNCORE_IIO_PMU_PATH "devices/uncore_iio_%d"
+#define SYSFS_UNCORE_PMU_PATH "%s/"UNCORE_IIO_PMU_PATH
+#define PLATFORM_MAPPING_PATH UNCORE_IIO_PMU_PATH"/die%d"
+
+/*
+ * Each metric requiries one IIO event which increments at every 4B transfer
+ * in corresponding direction. The formulas to compute metrics are generic:
+ * #EventCount * 4B / (1024 * 1024)
+ */
+static const char * const iostat_metrics[] = {
+ "Inbound Read(MB)",
+ "Inbound Write(MB)",
+ "Outbound Read(MB)",
+ "Outbound Write(MB)",
+};
+
+static inline int iostat_metrics_count(void)
+{
+ return sizeof(iostat_metrics) / sizeof(char *);
+}
+
+static const char *iostat_metric_by_idx(int idx)
+{
+ return *(iostat_metrics + idx % iostat_metrics_count());
+}
+
+struct iio_root_port {
+ u32 domain;
+ u8 bus;
+ u8 die;
+ u8 pmu_idx;
+ int idx;
+};
+
+struct iio_root_ports_list {
+ struct iio_root_port **rps;
+ int nr_entries;
+};
+
+static struct iio_root_ports_list *root_ports;
+
+static void iio_root_port_show(FILE *output,
+ const struct iio_root_port * const rp)
+{
+ if (output && rp)
+ fprintf(output, "S%d-uncore_iio_%d<%04x:%02x>\n",
+ rp->die, rp->pmu_idx, rp->domain, rp->bus);
+}
+
+static struct iio_root_port *iio_root_port_new(u32 domain, u8 bus,
+ u8 die, u8 pmu_idx)
+{
+ struct iio_root_port *p = calloc(1, sizeof(*p));
+
+ if (p) {
+ p->domain = domain;
+ p->bus = bus;
+ p->die = die;
+ p->pmu_idx = pmu_idx;
+ }
+ return p;
+}
+
+static void iio_root_ports_list_free(struct iio_root_ports_list *list)
+{
+ int idx;
+
+ if (list) {
+ for (idx = 0; idx < list->nr_entries; idx++)
+ free(list->rps[idx]);
+ free(list->rps);
+ free(list);
+ }
+}
+
+static struct iio_root_port *iio_root_port_find_by_notation(
+ const struct iio_root_ports_list * const list, u32 domain, u8 bus)
+{
+ int idx;
+ struct iio_root_port *rp;
+
+ if (list) {
+ for (idx = 0; idx < list->nr_entries; idx++) {
+ rp = list->rps[idx];
+ if (rp && rp->domain == domain && rp->bus == bus)
+ return rp;
+ }
+ }
+ return NULL;
+}
+
+static int iio_root_ports_list_insert(struct iio_root_ports_list *list,
+ struct iio_root_port * const rp)
+{
+ struct iio_root_port **tmp_buf;
+
+ if (list && rp) {
+ rp->idx = list->nr_entries++;
+ tmp_buf = realloc(list->rps,
+ list->nr_entries * sizeof(*list->rps));
+ if (!tmp_buf) {
+ pr_err("Failed to realloc memory\n");
+ return -ENOMEM;
+ }
+ tmp_buf[rp->idx] = rp;
+ list->rps = tmp_buf;
+ }
+ return 0;
+}
+
+static int iio_mapping(u8 pmu_idx, struct iio_root_ports_list * const list)
+{
+ char *buf;
+ char path[MAX_PATH];
+ u32 domain;
+ u8 bus;
+ struct iio_root_port *rp;
+ size_t size;
+ int ret;
+
+ for (int die = 0; die < cpu__max_node(); die++) {
+ scnprintf(path, MAX_PATH, PLATFORM_MAPPING_PATH, pmu_idx, die);
+ if (sysfs__read_str(path, &buf, &size) < 0) {
+ if (pmu_idx)
+ goto out;
+ pr_err("Mode iostat is not supported\n");
+ return -1;
+ }
+ ret = sscanf(buf, "%04x:%02hhx", &domain, &bus);
+ free(buf);
+ if (ret != 2) {
+ pr_err("Invalid mapping data: iio_%d; die%d\n",
+ pmu_idx, die);
+ return -1;
+ }
+ rp = iio_root_port_new(domain, bus, die, pmu_idx);
+ if (!rp || iio_root_ports_list_insert(list, rp)) {
+ free(rp);
+ return -ENOMEM;
+ }
+ }
+out:
+ return 0;
+}
+
+static u8 iio_pmu_count(void)
+{
+ u8 pmu_idx = 0;
+ char path[MAX_PATH];
+ const char *sysfs = sysfs__mountpoint();
+
+ if (sysfs) {
+ for (;; pmu_idx++) {
+ snprintf(path, sizeof(path), SYSFS_UNCORE_PMU_PATH,
+ sysfs, pmu_idx);
+ if (access(path, F_OK) != 0)
+ break;
+ }
+ }
+ return pmu_idx;
+}
+
+static int iio_root_ports_scan(struct iio_root_ports_list **list)
+{
+ int ret = -ENOMEM;
+ struct iio_root_ports_list *tmp_list;
+ u8 pmu_count = iio_pmu_count();
+
+ if (!pmu_count) {
+ pr_err("Unsupported uncore pmu configuration\n");
+ return -1;
+ }
+
+ tmp_list = calloc(1, sizeof(*tmp_list));
+ if (!tmp_list)
+ goto err;
+
+ for (u8 pmu_idx = 0; pmu_idx < pmu_count; pmu_idx++) {
+ ret = iio_mapping(pmu_idx, tmp_list);
+ if (ret)
+ break;
+ }
+err:
+ if (!ret)
+ *list = tmp_list;
+ else
+ iio_root_ports_list_free(tmp_list);
+
+ return ret;
+}
+
+static int iio_root_port_parse_str(u32 *domain, u8 *bus, char *str)
+{
+ int ret;
+ regex_t regex;
+ /*
+ * Expected format domain:bus:
+ * Valid domain range [0:ffff]
+ * Valid bus range [0:ff]
+ * Example: 0000:af, 0:3d, 01:7
+ */
+ regcomp(&regex, "^([a-f0-9A-F]{1,}):([a-f0-9A-F]{1,2})", REG_EXTENDED);
+ ret = regexec(&regex, str, 0, NULL, 0);
+ if (ret || sscanf(str, "%08x:%02hhx", domain, bus) != 2)
+ pr_warning("Unrecognized root port format: %s\n"
+ "Please use the following format:\n"
+ "\t [domain]:[bus]\n"
+ "\t for example: 0000:3d\n", str);
+
+ regfree(&regex);
+ return ret;
+}
+
+static int iio_root_ports_list_filter(struct iio_root_ports_list **list,
+ const char *filter)
+{
+ char *tok, *tmp, *filter_copy = NULL;
+ struct iio_root_port *rp;
+ u32 domain;
+ u8 bus;
+ int ret = -ENOMEM;
+ struct iio_root_ports_list *tmp_list = calloc(1, sizeof(*tmp_list));
+
+ if (!tmp_list)
+ goto err;
+
+ filter_copy = strdup(filter);
+ if (!filter_copy)
+ goto err;
+
+ for (tok = strtok_r(filter_copy, ",", &tmp); tok;
+ tok = strtok_r(NULL, ",", &tmp)) {
+ if (!iio_root_port_parse_str(&domain, &bus, tok)) {
+ rp = iio_root_port_find_by_notation(*list, domain, bus);
+ if (rp) {
+ (*list)->rps[rp->idx] = NULL;
+ ret = iio_root_ports_list_insert(tmp_list, rp);
+ if (ret) {
+ free(rp);
+ goto err;
+ }
+ } else if (!iio_root_port_find_by_notation(tmp_list,
+ domain, bus))
+ pr_warning("Root port %04x:%02x were not found\n",
+ domain, bus);
+ }
+ }
+
+ if (tmp_list->nr_entries == 0) {
+ pr_err("Requested root ports were not found\n");
+ ret = -EINVAL;
+ }
+err:
+ iio_root_ports_list_free(*list);
+ if (ret)
+ iio_root_ports_list_free(tmp_list);
+ else
+ *list = tmp_list;
+
+ free(filter_copy);
+ return ret;
+}
+
+static int iostat_event_group(struct evlist *evl,
+ struct iio_root_ports_list *list)
+{
+ int ret;
+ int idx;
+ const char *iostat_cmd_template =
+ "{uncore_iio_%x/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+ uncore_iio_%x/event=0x83,umask=0x01,ch_mask=0xF,fc_mask=0x07/,\
+ uncore_iio_%x/event=0xc0,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+ uncore_iio_%x/event=0xc0,umask=0x01,ch_mask=0xF,fc_mask=0x07/}";
+ const int len_template = strlen(iostat_cmd_template) + 1;
+ struct evsel *evsel = NULL;
+ int metrics_count = iostat_metrics_count();
+ char *iostat_cmd = calloc(len_template, 1);
+
+ if (!iostat_cmd)
+ return -ENOMEM;
+
+ for (idx = 0; idx < list->nr_entries; idx++) {
+ sprintf(iostat_cmd, iostat_cmd_template,
+ list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx,
+ list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx);
+ ret = parse_event(evl, iostat_cmd);
+ if (ret)
+ goto err;
+ }
+
+ evlist__for_each_entry(evl, evsel) {
+ evsel->priv = list->rps[evsel->core.idx / metrics_count];
+ }
+ list->nr_entries = 0;
+err:
+ iio_root_ports_list_free(list);
+ free(iostat_cmd);
+ return ret;
+}
+
+int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config)
+{
+ if (evlist->core.nr_entries > 0) {
+ pr_warning("The -e and -M options are not supported."
+ "All chosen events/metrics will be dropped\n");
+ evlist__delete(evlist);
+ evlist = evlist__new();
+ if (!evlist)
+ return -ENOMEM;
+ }
+
+ config->metric_only = true;
+ config->aggr_mode = AGGR_GLOBAL;
+
+ return iostat_event_group(evlist, root_ports);
+}
+
+int iostat_parse(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ int ret;
+ struct perf_stat_config *config = (struct perf_stat_config *)opt->data;
+
+ ret = iio_root_ports_scan(&root_ports);
+ if (!ret) {
+ config->iostat_run = true;
+ if (!str)
+ iostat_mode = IOSTAT_RUN;
+ else if (!strcmp(str, "list"))
+ iostat_mode = IOSTAT_LIST;
+ else {
+ iostat_mode = IOSTAT_RUN;
+ ret = iio_root_ports_list_filter(&root_ports, str);
+ }
+ }
+ return ret;
+}
+
+void iostat_list(struct evlist *evlist, struct perf_stat_config *config)
+{
+ struct evsel *evsel;
+ struct iio_root_port *rp = NULL;
+
+ evlist__for_each_entry(evlist, evsel) {
+ if (rp != evsel->priv) {
+ rp = evsel->priv;
+ iio_root_port_show(config->output, rp);
+ }
+ }
+}
+
+void iostat_release(struct evlist *evlist)
+{
+ struct evsel *evsel;
+ struct iio_root_port *rp = NULL;
+
+ evlist__for_each_entry(evlist, evsel) {
+ if (rp != evsel->priv) {
+ rp = evsel->priv;
+ free(evsel->priv);
+ }
+ }
+}
+
+void iostat_prefix(struct evlist *evlist,
+ struct perf_stat_config *config,
+ char *prefix, struct timespec *ts)
+{
+ struct iio_root_port *rp = evlist->selected->priv;
+
+ if (rp) {
+ if (ts)
+ sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s",
+ ts->tv_sec, ts->tv_nsec,
+ config->csv_sep, rp->domain, rp->bus,
+ config->csv_sep);
+ else
+ sprintf(prefix, "%04x:%02x%s", rp->domain, rp->bus,
+ config->csv_sep);
+ }
+}
+
+void iostat_print_header_prefix(struct perf_stat_config *config)
+{
+ if (config->csv_output)
+ fputs("port,", config->output);
+ else if (config->interval)
+ fprintf(config->output, "# time port ");
+ else
+ fprintf(config->output, " port ");
+}
+
+void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
+ struct perf_stat_output_ctx *out)
+{
+ double iostat_value = 0;
+ u64 prev_count_val = 0;
+ const char *iostat_metric = iostat_metric_by_idx(evsel->core.idx);
+ u8 die = ((struct iio_root_port *)evsel->priv)->die;
+ struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
+
+ if (count && count->run && count->ena) {
+ if (evsel->prev_raw_counts && !out->force_header) {
+ struct perf_counts_values *prev_count =
+ perf_counts(evsel->prev_raw_counts, die, 0);
+
+ prev_count_val = prev_count->val;
+ prev_count->val = count->val;
+ }
+ iostat_value = (count->val - prev_count_val) /
+ ((double) count->run / count->ena);
+ }
+ out->print_metric(config, out->ctx, NULL, "%8.0f", iostat_metric,
+ iostat_value / (256 * 1024));
+}
+
+void iostat_print_counters(struct evlist *evlist,
+ struct perf_stat_config *config, struct timespec *ts,
+ char *prefix, iostat_print_counter_t print_cnt_cb)
+{
+ void *perf_device = NULL;
+ struct evsel *counter = evlist__first(evlist);
+
+ evlist__set_selected(evlist, counter);
+ iostat_prefix(evlist, config, prefix, ts);
+ fprintf(config->output, "%s", prefix);
+ evlist__for_each_entry(evlist, counter) {
+ perf_device = evlist->selected->priv;
+ if (perf_device && perf_device != counter->priv) {
+ evlist__set_selected(evlist, counter);
+ iostat_prefix(evlist, config, prefix, ts);
+ fprintf(config->output, "\n%s", prefix);
+ }
+ print_cnt_cb(config, counter, prefix);
+ }
+ fputc('\n', config->output);
+}
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index c0775c39227f..c5dd54f6ef5e 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -31,8 +31,8 @@ const char *kvm_exit_trace = "kvm:kvm_exit";
static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample,
struct event_key *key)
{
- key->key = perf_evsel__intval(evsel, sample, "gpa");
- key->info = perf_evsel__intval(evsel, sample, "type");
+ key->key = evsel__intval(evsel, sample, "gpa");
+ key->info = evsel__intval(evsel, sample, "type");
}
#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
@@ -48,7 +48,7 @@ static bool mmio_event_begin(struct evsel *evsel,
/* MMIO write begin event in kernel. */
if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
- perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+ evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
mmio_event_get_key(evsel, sample, key);
return true;
}
@@ -65,7 +65,7 @@ static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample,
/* MMIO read end event in kernel.*/
if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
- perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+ evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
mmio_event_get_key(evsel, sample, key);
return true;
}
@@ -94,8 +94,8 @@ static void ioport_event_get_key(struct evsel *evsel,
struct perf_sample *sample,
struct event_key *key)
{
- key->key = perf_evsel__intval(evsel, sample, "port");
- key->info = perf_evsel__intval(evsel, sample, "rw");
+ key->key = evsel__intval(evsel, sample, "port");
+ key->info = evsel__intval(evsel, sample, "rw");
}
static bool ioport_event_begin(struct evsel *evsel,
@@ -133,11 +133,56 @@ static struct kvm_events_ops ioport_events = {
.name = "IO Port Access"
};
+ /* The time of emulation msr is from kvm_msr to kvm_entry. */
+static void msr_event_get_key(struct evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = evsel__intval(evsel, sample, "ecx");
+ key->info = evsel__intval(evsel, sample, "write");
+}
+
+static bool msr_event_begin(struct evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ if (!strcmp(evsel->name, "kvm:kvm_msr")) {
+ msr_event_get_key(evsel, sample, key);
+ return true;
+ }
+
+ return false;
+}
+
+static bool msr_event_end(struct evsel *evsel,
+ struct perf_sample *sample __maybe_unused,
+ struct event_key *key __maybe_unused)
+{
+ return kvm_entry_event(evsel);
+}
+
+static void msr_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+ struct event_key *key,
+ char *decode)
+{
+ scnprintf(decode, decode_str_len, "%#llx:%s",
+ (unsigned long long)key->key,
+ key->info ? "W" : "R");
+}
+
+static struct kvm_events_ops msr_events = {
+ .is_begin_event = msr_event_begin,
+ .is_end_event = msr_event_end,
+ .decode_key = msr_event_decode_key,
+ .name = "MSR Access"
+};
+
const char *kvm_events_tp[] = {
"kvm:kvm_entry",
"kvm:kvm_exit",
"kvm:kvm_mmio",
"kvm:kvm_pio",
+ "kvm:kvm_msr",
NULL,
};
@@ -145,6 +190,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = {
{ .name = "vmexit", .ops = &exit_events },
{ .name = "mmio", .ops = &mmio_events },
{ .name = "ioport", .ops = &ioport_events },
+ { .name = "msr", .ops = &msr_events },
{ NULL, NULL },
};
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
new file mode 100644
index 000000000000..f683ac702247
--- /dev/null
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/pmu.h"
+#include "util/env.h"
+#include "map_symbol.h"
+#include "mem-events.h"
+#include "linux/string.h"
+
+static char mem_loads_name[100];
+static bool mem_loads_name__init;
+static char mem_stores_name[100];
+
+#define MEM_LOADS_AUX 0x8203
+#define MEM_LOADS_AUX_NAME "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+static struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
+ E("ldlat-loads", "%s/mem-loads,ldlat=%u/P", "%s/events/mem-loads"),
+ E("ldlat-stores", "%s/mem-stores/P", "%s/events/mem-stores"),
+ E(NULL, NULL, NULL),
+};
+
+static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+ E(NULL, NULL, NULL),
+ E(NULL, NULL, NULL),
+ E("mem-ldst", "ibs_op//", "ibs_op"),
+};
+
+static int perf_mem_is_amd_cpu(void)
+{
+ struct perf_env env = { .total_mem = 0, };
+
+ perf_env__cpuid(&env);
+ if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
+ return 1;
+ return -1;
+}
+
+struct perf_mem_event *perf_mem_events__ptr(int i)
+{
+ /* 0: Uninitialized, 1: Yes, -1: No */
+ static int is_amd;
+
+ if (i >= PERF_MEM_EVENTS__MAX)
+ return NULL;
+
+ if (!is_amd)
+ is_amd = perf_mem_is_amd_cpu();
+
+ if (is_amd == 1)
+ return &perf_mem_events_amd[i];
+
+ return &perf_mem_events_intel[i];
+}
+
+bool is_mem_loads_aux_event(struct evsel *leader)
+{
+ if (perf_pmu__find("cpu")) {
+ if (!pmu_have_event("cpu", "mem-loads-aux"))
+ return false;
+ } else if (perf_pmu__find("cpu_core")) {
+ if (!pmu_have_event("cpu_core", "mem-loads-aux"))
+ return false;
+ }
+
+ return leader->core.attr.config == MEM_LOADS_AUX;
+}
+
+char *perf_mem_events__name(int i, char *pmu_name)
+{
+ struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+ if (!e)
+ return NULL;
+
+ if (i == PERF_MEM_EVENTS__LOAD) {
+ if (mem_loads_name__init && !pmu_name)
+ return mem_loads_name;
+
+ if (!pmu_name) {
+ mem_loads_name__init = true;
+ pmu_name = (char *)"cpu";
+ }
+
+ if (pmu_have_event(pmu_name, "mem-loads-aux")) {
+ scnprintf(mem_loads_name, sizeof(mem_loads_name),
+ MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
+ perf_mem_events__loads_ldlat);
+ } else {
+ scnprintf(mem_loads_name, sizeof(mem_loads_name),
+ e->name, pmu_name,
+ perf_mem_events__loads_ldlat);
+ }
+ return mem_loads_name;
+ }
+
+ if (i == PERF_MEM_EVENTS__STORE) {
+ if (!pmu_name)
+ pmu_name = (char *)"cpu";
+
+ scnprintf(mem_stores_name, sizeof(mem_stores_name),
+ e->name, pmu_name);
+ return mem_stores_name;
+ }
+
+ return (char *)e->name;
+}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index fca81b39b09f..0ed177991ad0 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -9,6 +9,8 @@
#include "../../../util/perf_regs.h"
#include "../../../util/debug.h"
#include "../../../util/event.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmu-hybrid.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(AX, PERF_REG_X86_AX),
@@ -165,7 +167,7 @@ static int sdt_init_op_regex(void)
/*
* Max x86 register name length is 5(ex: %r15d). So, 6th char
* should always contain NULL. This helps to find register name
- * length using strlen, insted of maintaing one more variable.
+ * length using strlen, instead of maintaining one more variable.
*/
#define SDT_REG_NAME_SIZE 6
@@ -207,7 +209,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
* and displacement 0 (Both sign and displacement 0 are
* optional so it may be empty). Use one more character
* to hold last NULL so that strlen can be used to find
- * prefix length, instead of maintaing one more variable.
+ * prefix length, instead of maintaining one more variable.
*/
char prefix[3] = {0};
@@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void)
.disabled = 1,
.exclude_kernel = 1,
};
+ struct perf_pmu *pmu;
int fd;
/*
* In an unnamed union, init it here to build on older gcc versions
*/
attr.sample_period = 1;
+ if (perf_pmu__has_hybrid()) {
+ /*
+ * The same register set is supported among different hybrid PMUs.
+ * Only check the first available one.
+ */
+ pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list);
+ attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+ }
+
event_attr_init(&attr);
fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index d48d608517fd..74d69db1ea99 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,12 +1,30 @@
// SPDX-License-Identifier: GPL-2.0
#include <string.h>
-
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <fcntl.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
+#include <linux/zalloc.h>
+#include <api/fs/fs.h>
+#include <errno.h>
#include "../../../util/intel-pt.h"
#include "../../../util/intel-bts.h"
#include "../../../util/pmu.h"
+#include "../../../util/fncache.h"
+
+#define TEMPLATE_ALIAS "%s/bus/event_source/devices/%s/alias"
+
+struct pmu_alias {
+ char *name;
+ char *alias;
+ struct list_head list;
+};
+
+static LIST_HEAD(pmu_alias_name_list);
+static bool cached_list;
struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
{
@@ -18,3 +36,138 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __mayb
#endif
return NULL;
}
+
+static void pmu_alias__delete(struct pmu_alias *pmu_alias)
+{
+ if (!pmu_alias)
+ return;
+
+ zfree(&pmu_alias->name);
+ zfree(&pmu_alias->alias);
+ free(pmu_alias);
+}
+
+static struct pmu_alias *pmu_alias__new(char *name, char *alias)
+{
+ struct pmu_alias *pmu_alias = zalloc(sizeof(*pmu_alias));
+
+ if (pmu_alias) {
+ pmu_alias->name = strdup(name);
+ if (!pmu_alias->name)
+ goto out_delete;
+
+ pmu_alias->alias = strdup(alias);
+ if (!pmu_alias->alias)
+ goto out_delete;
+ }
+ return pmu_alias;
+
+out_delete:
+ pmu_alias__delete(pmu_alias);
+ return NULL;
+}
+
+static int setup_pmu_alias_list(void)
+{
+ char path[PATH_MAX];
+ DIR *dir;
+ struct dirent *dent;
+ const char *sysfs = sysfs__mountpoint();
+ struct pmu_alias *pmu_alias;
+ char buf[MAX_PMU_NAME_LEN];
+ FILE *file;
+ int ret = -ENOMEM;
+
+ if (!sysfs)
+ return -1;
+
+ snprintf(path, PATH_MAX,
+ "%s" EVENT_SOURCE_DEVICE_PATH, sysfs);
+
+ dir = opendir(path);
+ if (!dir)
+ return -errno;
+
+ while ((dent = readdir(dir))) {
+ if (!strcmp(dent->d_name, ".") ||
+ !strcmp(dent->d_name, ".."))
+ continue;
+
+ snprintf(path, PATH_MAX,
+ TEMPLATE_ALIAS, sysfs, dent->d_name);
+
+ if (!file_available(path))
+ continue;
+
+ file = fopen(path, "r");
+ if (!file)
+ continue;
+
+ if (!fgets(buf, sizeof(buf), file)) {
+ fclose(file);
+ continue;
+ }
+
+ fclose(file);
+
+ /* Remove the last '\n' */
+ buf[strlen(buf) - 1] = 0;
+
+ pmu_alias = pmu_alias__new(dent->d_name, buf);
+ if (!pmu_alias)
+ goto close_dir;
+
+ list_add_tail(&pmu_alias->list, &pmu_alias_name_list);
+ }
+
+ ret = 0;
+
+close_dir:
+ closedir(dir);
+ return ret;
+}
+
+static char *__pmu_find_real_name(const char *name)
+{
+ struct pmu_alias *pmu_alias;
+
+ list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) {
+ if (!strcmp(name, pmu_alias->alias))
+ return pmu_alias->name;
+ }
+
+ return (char *)name;
+}
+
+char *pmu_find_real_name(const char *name)
+{
+ if (cached_list)
+ return __pmu_find_real_name(name);
+
+ setup_pmu_alias_list();
+ cached_list = true;
+
+ return __pmu_find_real_name(name);
+}
+
+static char *__pmu_find_alias_name(const char *name)
+{
+ struct pmu_alias *pmu_alias;
+
+ list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) {
+ if (!strcmp(name, pmu_alias->name))
+ return pmu_alias->alias;
+ }
+ return NULL;
+}
+
+char *pmu_find_alias_name(const char *name)
+{
+ if (cached_list)
+ return __pmu_find_alias_name(name);
+
+ setup_pmu_alias_list();
+ cached_list = true;
+
+ return __pmu_find_alias_name(name);
+}
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
new file mode 100644
index 000000000000..54810f9acd6f
--- /dev/null
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/pmu.h"
+#include "util/topdown.h"
+#include "util/evlist.h"
+#include "util/debug.h"
+#include "util/pmu-hybrid.h"
+#include "topdown.h"
+#include "evsel.h"
+
+#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
+#define TOPDOWN_L1_EVENTS_CORE "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/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}"
+#define TOPDOWN_L2_EVENTS_CORE "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/,cpu_core/topdown-heavy-ops/,cpu_core/topdown-br-mispredict/,cpu_core/topdown-fetch-lat/,cpu_core/topdown-mem-bound/}"
+
+/* 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.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool arch_topdown_check_group(bool *warn)
+{
+ int n;
+
+ if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+ return false;
+ if (n > 0) {
+ *warn = true;
+ return false;
+ }
+ return true;
+}
+
+void arch_topdown_group_warn(void)
+{
+ fprintf(stderr,
+ "nmi_watchdog enabled with topdown. May give wrong results.\n"
+ "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+#define TOPDOWN_SLOTS 0x0400
+
+/*
+ * Check whether a topdown group supports sample-read.
+ *
+ * Only Topdown metric supports sample-read. The slots
+ * event must be the leader of the topdown group.
+ */
+
+bool arch_topdown_sample_read(struct evsel *leader)
+{
+ if (!evsel__sys_has_perf_metrics(leader))
+ return false;
+
+ if (leader->core.attr.config == TOPDOWN_SLOTS)
+ return true;
+
+ return false;
+}
+
+const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn)
+{
+ const char *pmu_name;
+
+ if (!perf_pmu__has_hybrid())
+ return "cpu";
+
+ if (!evlist->hybrid_pmu_name) {
+ if (warn)
+ pr_warning("WARNING: default to use cpu_core topdown events\n");
+ evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu("core");
+ }
+
+ pmu_name = evlist->hybrid_pmu_name;
+
+ return pmu_name;
+}
+
+int topdown_parse_events(struct evlist *evlist)
+{
+ const char *topdown_events;
+ const char *pmu_name;
+
+ if (!topdown_sys_has_perf_metrics())
+ return 0;
+
+ pmu_name = arch_get_topdown_pmu_name(evlist, false);
+
+ if (pmu_have_event(pmu_name, "topdown-heavy-ops")) {
+ if (!strcmp(pmu_name, "cpu_core"))
+ topdown_events = TOPDOWN_L2_EVENTS_CORE;
+ else
+ topdown_events = TOPDOWN_L2_EVENTS;
+ } else {
+ if (!strcmp(pmu_name, "cpu_core"))
+ topdown_events = TOPDOWN_L1_EVENTS_CORE;
+ else
+ topdown_events = TOPDOWN_L1_EVENTS;
+ }
+
+ return parse_event(evlist, topdown_events);
+}
diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
new file mode 100644
index 000000000000..7eb81f042838
--- /dev/null
+++ b/tools/perf/arch/x86/util/topdown.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOPDOWN_H
+#define _TOPDOWN_H 1
+
+bool topdown_sys_has_perf_metrics(void);
+int topdown_parse_events(struct evlist *evlist);
+
+#endif
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 2f55afb14e1f..eb2b5195bd02 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -1,84 +1,90 @@
// SPDX-License-Identifier: GPL-2.0
-#include <stdbool.h>
-#include <errno.h>
-
-#include <linux/stddef.h>
-#include <linux/perf_event.h>
-
#include <linux/types.h>
-#include <asm/barrier.h>
+#include <math.h>
+#include <string.h>
+
#include "../../../util/debug.h"
-#include "../../../util/event.h"
-#include "../../../util/synthetic-events.h"
#include "../../../util/tsc.h"
+#include "cpuid.h"
-int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
- struct perf_tsc_conversion *tc)
+u64 rdtsc(void)
{
- bool cap_user_time_zero;
- u32 seq;
- int i = 0;
-
- while (1) {
- seq = pc->lock;
- rmb();
- tc->time_mult = pc->time_mult;
- tc->time_shift = pc->time_shift;
- tc->time_zero = pc->time_zero;
- cap_user_time_zero = pc->cap_user_time_zero;
- rmb();
- if (pc->lock == seq && !(seq & 1))
- break;
- if (++i > 10000) {
- pr_debug("failed to get perf_event_mmap_page lock\n");
- return -EINVAL;
- }
- }
+ unsigned int low, high;
- if (!cap_user_time_zero)
- return -EOPNOTSUPP;
+ asm volatile("rdtsc" : "=a" (low), "=d" (high));
- return 0;
+ return low | ((u64)high) << 32;
}
-u64 rdtsc(void)
+/*
+ * Derive the TSC frequency in Hz from the /proc/cpuinfo, for example:
+ * ...
+ * model name : Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
+ * ...
+ * will return 3000000000.
+ */
+static double cpuinfo_tsc_freq(void)
{
- unsigned int low, high;
+ double result = 0;
+ FILE *cpuinfo;
+ char *line = NULL;
+ size_t len = 0;
- asm volatile("rdtsc" : "=a" (low), "=d" (high));
+ cpuinfo = fopen("/proc/cpuinfo", "r");
+ if (!cpuinfo) {
+ pr_err("Failed to read /proc/cpuinfo for TSC frequency");
+ return NAN;
+ }
+ while (getline(&line, &len, cpuinfo) > 0) {
+ if (!strncmp(line, "model name", 10)) {
+ char *pos = strstr(line + 11, " @ ");
- return low | ((u64)high) << 32;
+ if (pos && sscanf(pos, " @ %lfGHz", &result) == 1) {
+ result *= 1000000000;
+ goto out;
+ }
+ }
+ }
+out:
+ if (fpclassify(result) == FP_ZERO)
+ pr_err("Failed to find TSC frequency in /proc/cpuinfo");
+
+ free(line);
+ fclose(cpuinfo);
+ return result;
}
-int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
- struct perf_tool *tool,
- perf_event__handler_t process,
- struct machine *machine)
+double arch_get_tsc_freq(void)
{
- union perf_event event = {
- .time_conv = {
- .header = {
- .type = PERF_RECORD_TIME_CONV,
- .size = sizeof(struct perf_record_time_conv),
- },
- },
- };
- struct perf_tsc_conversion tc;
- int err;
+ unsigned int a, b, c, d, lvl;
+ static bool cached;
+ static double tsc;
+ char vendor[16];
- if (!pc)
- return 0;
- err = perf_read_tsc_conversion(pc, &tc);
- if (err == -EOPNOTSUPP)
+ if (cached)
+ return tsc;
+
+ cached = true;
+ get_cpuid_0(vendor, &lvl);
+ if (!strstr(vendor, "Intel"))
return 0;
- if (err)
- return err;
- pr_debug2("Synthesizing TSC conversion information\n");
+ /*
+ * Don't support Time Stamp Counter and
+ * Nominal Core Crystal Clock Information Leaf.
+ */
+ if (lvl < 0x15) {
+ tsc = cpuinfo_tsc_freq();
+ return tsc;
+ }
- event.time_conv.time_mult = tc.time_mult;
- event.time_conv.time_shift = tc.time_shift;
- event.time_conv.time_zero = tc.time_zero;
+ cpuid(0x15, 0, &a, &b, &c, &d);
+ /* TSC frequency is not enumerated */
+ if (!a || !b || !c) {
+ tsc = cpuinfo_tsc_freq();
+ return tsc;
+ }
- return process(tool, &event, NULL, machine);
+ tsc = (double)c * (double)b / (double)a;
+ return tsc;
}
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
index fda8f4206ee4..eea2bf87232b 100644
--- a/tools/perf/arch/x86/util/unwind-libdw.c
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -1,8 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include <elfutils/libdwfl.h>
-#include "../../util/unwind-libdw.h"
-#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../../util/unwind-libdw.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/event.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.