* [PATCH 01/44] perf header: Add AUX area tracing feature
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 2:58 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 02/44] perf evlist: Add support for mmapping an AUX area buffer Adrian Hunter
` (42 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add a feature to indicate that a perf.data file
contains AUX area data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
| 14 ++++++++++++++
| 1 +
2 files changed, 15 insertions(+)
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fff3b2a..a93c466 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,13 @@ static int write_branch_stack(int fd __maybe_unused,
return 0;
}
+static int write_auxtrace(int fd __maybe_unused,
+ struct perf_header *h __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ return 0;
+}
+
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1151,6 +1158,12 @@ static void print_branch_stack(struct perf_header *ph __maybe_unused,
fprintf(fp, "# contains samples with branch stack\n");
}
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+ int fd __maybe_unused, FILE *fp)
+{
+ fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1861,6 +1874,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
+ FEAT_OPA(HEADER_AUXTRACE, auxtrace),
};
struct header_print_data {
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac..d4d5796 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@ enum {
HEADER_BRANCH_STACK,
HEADER_PMU_MAPPINGS,
HEADER_GROUP_DESC,
+ HEADER_AUXTRACE,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf header: Add AUX area tracing feature
2015-04-09 15:53 ` [PATCH 01/44] perf header: Add AUX area tracing feature Adrian Hunter
@ 2015-05-06 2:58 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:58 UTC (permalink / raw)
To: linux-tip-commits
Cc: hpa, jolsa, fweisbec, acme, tglx, namhyung, linux-kernel,
dsahern, mingo, eranian, adrian.hunter, peterz
Commit-ID: 4025ea4024c271cc0d993b8641249dce33a63fcc
Gitweb: http://git.kernel.org/tip/4025ea4024c271cc0d993b8641249dce33a63fcc
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:41 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:49 -0300
perf header: Add AUX area tracing feature
Add a feature to indicate that a perf.data file contains AUX area data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
| 14 ++++++++++++++
| 1 +
2 files changed, 15 insertions(+)
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 918fd8a..589c280 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,13 @@ static int write_branch_stack(int fd __maybe_unused,
return 0;
}
+static int write_auxtrace(int fd __maybe_unused,
+ struct perf_header *h __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ return 0;
+}
+
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1151,6 +1158,12 @@ static void print_branch_stack(struct perf_header *ph __maybe_unused,
fprintf(fp, "# contains samples with branch stack\n");
}
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+ int fd __maybe_unused, FILE *fp)
+{
+ fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1861,6 +1874,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
+ FEAT_OPA(HEADER_AUXTRACE, auxtrace),
};
struct header_print_data {
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac..d4d5796 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@ enum {
HEADER_BRANCH_STACK,
HEADER_PMU_MAPPINGS,
HEADER_GROUP_DESC,
+ HEADER_AUXTRACE,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 02/44] perf evlist: Add support for mmapping an AUX area buffer
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
2015-04-09 15:53 ` [PATCH 01/44] perf header: Add AUX area tracing feature Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 2:58 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 03/44] perf tools: Add user events for AUX area tracing Adrian Hunter
` (41 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
This patch supports the addition to the kernel
of AUX area buffers that can be mmapped separately
from the perf-events buffer.
The AUX buffer can be configured to contain
hardware-produced trace information. The first
implementation will support Intel BTS and Intel PT.
One auxtrace buffer is mmapped per perf-events buffer.
If the requested auxtrace buffer size is zero, which
it will be until further support is added, then
no auxtrace mmapping is attempted.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/auxtrace.c | 113 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 117 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/evlist.c | 61 +++++++++++++++++++++--
tools/perf/util/evlist.h | 5 ++
5 files changed, 294 insertions(+), 3 deletions(-)
create mode 100644 tools/perf/util/auxtrace.c
create mode 100644 tools/perf/util/auxtrace.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a..b6c3f39 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -74,6 +74,7 @@ libperf-y += data.o
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
+libperf-y += auxtrace.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 0000000..dedb646
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,113 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd)
+{
+ struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pr_err("Cannot use AUX area tracing mmaps\n");
+ return -1;
+#endif
+
+ WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+ mm->userpg = userpg;
+ mm->mask = mp->mask;
+ mm->len = mp->len;
+ mm->prev = 0;
+ mm->idx = mp->idx;
+ mm->tid = mp->tid;
+ mm->cpu = mp->cpu;
+
+ if (!mp->len) {
+ mm->base = NULL;
+ return 0;
+ }
+
+ pc->aux_offset = mp->offset;
+ pc->aux_size = mp->len;
+
+ mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+ if (mm->base == MAP_FAILED) {
+ pr_debug2("failed to mmap AUX area\n");
+ mm->base = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+ if (mm->base) {
+ munmap(mm->base, mm->len);
+ mm->base = NULL;
+ }
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
+{
+ if (auxtrace_pages) {
+ mp->offset = auxtrace_offset;
+ mp->len = auxtrace_pages * (size_t)page_size;
+ mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+ mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+ pr_debug2("AUX area mmap length %zu\n", mp->len);
+ } else {
+ mp->len = 0;
+ }
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu)
+{
+ mp->idx = idx;
+
+ if (per_cpu) {
+ mp->cpu = evlist->cpus->map[idx];
+ if (evlist->threads)
+ mp->tid = evlist->threads->map[0];
+ else
+ mp->tid = -1;
+ } else {
+ mp->cpu = -1;
+ mp->tid = evlist->threads->map[idx];
+ }
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 0000000..2071b36
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,117 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+
+struct perf_evlist;
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+ void *base;
+ void *userpg;
+ size_t mask;
+ size_t len;
+ u64 prev;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+ size_t mask;
+ off_t offset;
+ size_t len;
+ int prot;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+ u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 old_tail;
+#endif
+
+ /* Ensure all reads are done before we write the tail out */
+ mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pc->aux_tail = tail;
+#else
+ do {
+ old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+ } while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 76ef7ee..a588e01 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -725,6 +725,34 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
perf_evlist__mmap_put(evlist, idx);
}
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ void *userpg __maybe_unused,
+ int fd __maybe_unused)
+{
+ return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ off_t auxtrace_offset __maybe_unused,
+ unsigned int auxtrace_pages __maybe_unused,
+ bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ int idx __maybe_unused,
+ bool per_cpu __maybe_unused)
+{
+}
+
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
{
if (evlist->mmap[idx].base != NULL) {
@@ -732,6 +760,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
evlist->mmap[idx].base = NULL;
evlist->mmap[idx].refcnt = 0;
}
+ auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
}
void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +788,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
struct mmap_params {
int prot;
int mask;
+ struct auxtrace_mmap_params auxtrace_mp;
};
static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -789,6 +819,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
return -1;
}
+ if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+ &mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+ return -1;
+
return 0;
}
@@ -853,6 +887,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
for (cpu = 0; cpu < nr_cpus; cpu++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+ true);
+
for (thread = 0; thread < nr_threads; thread++) {
if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
thread, &output))
@@ -878,6 +915,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+ false);
+
if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
&output))
goto out_unmap;
@@ -981,19 +1021,25 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
}
/**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
* @pages: map length in pages
* @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
*
* If @overwrite is %false the user needs to signal event consumption using
* perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
* automatically.
*
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
* Return: %0 on success, negative error code otherwise.
*/
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
- bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1059,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
+ auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+ auxtrace_pages, auxtrace_overwrite);
+
evlist__for_each(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
@@ -1026,6 +1075,12 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
return perf_evlist__mmap_per_cpu(evlist, &mp);
}
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite)
+{
+ return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
evlist->threads = thread_map__new_str(target->pid, target->tid,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index fb19c47..beed571 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -8,6 +8,7 @@
#include "event.h"
#include "evsel.h"
#include "util.h"
+#include "auxtrace.h"
#include <unistd.h>
struct pollfd;
@@ -28,6 +29,7 @@ struct perf_mmap {
int mask;
int refcnt;
unsigned int prev;
+ struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
@@ -126,6 +128,9 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf evlist: Add support for mmapping an AUX area buffer
2015-04-09 15:53 ` [PATCH 02/44] perf evlist: Add support for mmapping an AUX area buffer Adrian Hunter
@ 2015-05-06 2:58 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:58 UTC (permalink / raw)
To: linux-tip-commits
Cc: mingo, hpa, linux-kernel, acme, fweisbec, tglx, peterz, eranian,
dsahern, namhyung, jolsa, adrian.hunter
Commit-ID: 718c602d67aac04a48cd8e444e778cc3d5d9027f
Gitweb: http://git.kernel.org/tip/718c602d67aac04a48cd8e444e778cc3d5d9027f
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:42 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:50 -0300
perf evlist: Add support for mmapping an AUX area buffer
This patch supports the addition to the kernel of AUX area buffers that
can be mmapped separately from the perf-events buffer.
The AUX buffer can be configured to contain hardware-produced trace
information. The first implementation will support Intel BTS and Intel
PT.
One auxtrace buffer is mmapped per perf-events buffer. If the requested
auxtrace buffer size is zero, which it will be until further support is
added, then no auxtrace mmapping is attempted.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-3-git-send-email-adrian.hunter@intel.com
[ Fixed conflict in evlist.h ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/auxtrace.c | 113 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 117 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/evlist.c | 61 +++++++++++++++++++++--
tools/perf/util/evlist.h | 5 ++
5 files changed, 294 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a..b6c3f39 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -74,6 +74,7 @@ libperf-y += data.o
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
+libperf-y += auxtrace.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 0000000..dedb646
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,113 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd)
+{
+ struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pr_err("Cannot use AUX area tracing mmaps\n");
+ return -1;
+#endif
+
+ WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+ mm->userpg = userpg;
+ mm->mask = mp->mask;
+ mm->len = mp->len;
+ mm->prev = 0;
+ mm->idx = mp->idx;
+ mm->tid = mp->tid;
+ mm->cpu = mp->cpu;
+
+ if (!mp->len) {
+ mm->base = NULL;
+ return 0;
+ }
+
+ pc->aux_offset = mp->offset;
+ pc->aux_size = mp->len;
+
+ mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+ if (mm->base == MAP_FAILED) {
+ pr_debug2("failed to mmap AUX area\n");
+ mm->base = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+ if (mm->base) {
+ munmap(mm->base, mm->len);
+ mm->base = NULL;
+ }
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
+{
+ if (auxtrace_pages) {
+ mp->offset = auxtrace_offset;
+ mp->len = auxtrace_pages * (size_t)page_size;
+ mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+ mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+ pr_debug2("AUX area mmap length %zu\n", mp->len);
+ } else {
+ mp->len = 0;
+ }
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu)
+{
+ mp->idx = idx;
+
+ if (per_cpu) {
+ mp->cpu = evlist->cpus->map[idx];
+ if (evlist->threads)
+ mp->tid = evlist->threads->map[0];
+ else
+ mp->tid = -1;
+ } else {
+ mp->cpu = -1;
+ mp->tid = evlist->threads->map[idx];
+ }
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 0000000..2071b36
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,117 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+
+struct perf_evlist;
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+ void *base;
+ void *userpg;
+ size_t mask;
+ size_t len;
+ u64 prev;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+ size_t mask;
+ off_t offset;
+ size_t len;
+ int prot;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+ u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 old_tail;
+#endif
+
+ /* Ensure all reads are done before we write the tail out */
+ mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pc->aux_tail = tail;
+#else
+ do {
+ old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+ } while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 080be93..5b26f45 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -725,6 +725,34 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
perf_evlist__mmap_put(evlist, idx);
}
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ void *userpg __maybe_unused,
+ int fd __maybe_unused)
+{
+ return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ off_t auxtrace_offset __maybe_unused,
+ unsigned int auxtrace_pages __maybe_unused,
+ bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ int idx __maybe_unused,
+ bool per_cpu __maybe_unused)
+{
+}
+
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
{
if (evlist->mmap[idx].base != NULL) {
@@ -732,6 +760,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
evlist->mmap[idx].base = NULL;
evlist->mmap[idx].refcnt = 0;
}
+ auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
}
void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +788,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
struct mmap_params {
int prot;
int mask;
+ struct auxtrace_mmap_params auxtrace_mp;
};
static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -789,6 +819,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
return -1;
}
+ if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+ &mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+ return -1;
+
return 0;
}
@@ -853,6 +887,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
for (cpu = 0; cpu < nr_cpus; cpu++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+ true);
+
for (thread = 0; thread < nr_threads; thread++) {
if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
thread, &output))
@@ -878,6 +915,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+ false);
+
if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
&output))
goto out_unmap;
@@ -981,19 +1021,25 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
}
/**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
* @pages: map length in pages
* @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
*
* If @overwrite is %false the user needs to signal event consumption using
* perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
* automatically.
*
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
* Return: %0 on success, negative error code otherwise.
*/
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
- bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1059,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
+ auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+ auxtrace_pages, auxtrace_overwrite);
+
evlist__for_each(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
@@ -1026,6 +1075,12 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
return perf_evlist__mmap_per_cpu(evlist, &mp);
}
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite)
+{
+ return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
evlist->threads = thread_map__new_str(target->pid, target->tid,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b5cce95..8dc986d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -8,6 +8,7 @@
#include "event.h"
#include "evsel.h"
#include "util.h"
+#include "auxtrace.h"
#include <unistd.h>
struct pollfd;
@@ -28,6 +29,7 @@ struct perf_mmap {
int mask;
int refcnt;
u64 prev;
+ struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
@@ -126,6 +128,9 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 03/44] perf tools: Add user events for AUX area tracing
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
2015-04-09 15:53 ` [PATCH 01/44] perf header: Add AUX area tracing feature Adrian Hunter
2015-04-09 15:53 ` [PATCH 02/44] perf evlist: Add support for mmapping an AUX area buffer Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-20 23:06 ` Arnaldo Carvalho de Melo
2015-05-06 2:59 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 04/44] perf tools: Add support for AUX area recording Adrian Hunter
` (40 subsequent siblings)
43 siblings, 2 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add two user events for AUX area tracing.
PERF_RECORD_AUXTRACE_INFO contains metadata,
consisting primarily the type of the
AUX area tracing data plus some amount
of architecture-specific information.
There should be only one
PERF_RECORD_AUXTRACE_INFO event.
PERF_RECORD_AUXTRACE identifies AUX area
tracing data copied from the mmapped
AUX area tracing region. The actual
data is not part of the event but
immediately follows it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/event.c | 2 ++
tools/perf/util/event.h | 22 +++++++++++++++
tools/perf/util/session.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/tool.h | 9 ++++++-
4 files changed, 101 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 5516236..07186ba 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -29,6 +29,8 @@ static const char *perf_event__names[] = {
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
+ [PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
+ [PERF_RECORD_AUXTRACE] = "AUXTRACE",
};
const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d..6d81bec 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -215,6 +215,8 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_FINISHED_ROUND = 68,
PERF_RECORD_ID_INDEX = 69,
+ PERF_RECORD_AUXTRACE_INFO = 70,
+ PERF_RECORD_AUXTRACE = 71,
PERF_RECORD_HEADER_MAX
};
@@ -280,6 +282,24 @@ struct id_index_event {
struct id_index_entry entries[0];
};
+struct auxtrace_info_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 reserved__; /* For alignment */
+ u64 priv[];
+};
+
+struct auxtrace_event {
+ struct perf_event_header header;
+ u64 size;
+ u64 offset;
+ u64 reference;
+ u32 idx;
+ u32 tid;
+ u32 cpu;
+ u32 reserved__; /* For alignment */
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -295,6 +315,8 @@ union perf_event {
struct tracing_data_event tracing_data;
struct build_id_event build_id;
struct id_index_event id_index;
+ struct auxtrace_info_event auxtrace_info;
+ struct auxtrace_event auxtrace;
};
void perf_event__print_totals(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c74012..cc78568 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -262,6 +262,40 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
return 0;
}
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+ char buf[4096];
+ ssize_t ret;
+
+ while (n > 0) {
+ ret = read(fd, buf, MIN(n, sizeof(buf)));
+ if (ret <= 0)
+ return ret;
+ n -= ret;
+ }
+
+ return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ if (perf_data_file__is_pipe(session->file))
+ skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+ return event->auxtrace.size;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@@ -298,6 +332,10 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
}
if (tool->id_index == NULL)
tool->id_index = process_id_index_stub;
+ if (tool->auxtrace_info == NULL)
+ tool->auxtrace_info = process_event_auxtrace_info_stub;
+ if (tool->auxtrace == NULL)
+ tool->auxtrace = process_event_auxtrace_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@@ -478,6 +516,29 @@ static void perf_event__tracing_data_swap(union perf_event *event,
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ size_t size;
+
+ event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+ size = event->header.size;
+ size -= (void *)&event->auxtrace_info.priv - (void *)event;
+ mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace.size = bswap_64(event->auxtrace.size);
+ event->auxtrace.offset = bswap_64(event->auxtrace.offset);
+ event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+ event->auxtrace.idx = bswap_32(event->auxtrace.idx);
+ event->auxtrace.tid = bswap_32(event->auxtrace.tid);
+ event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@@ -497,6 +558,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
[PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
+ [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
+ [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -980,6 +1043,12 @@ static s64 perf_session__process_user_event(struct perf_session *session,
return tool->finished_round(tool, event, oe);
case PERF_RECORD_ID_INDEX:
return tool->id_index(tool, event, session);
+ case PERF_RECORD_AUXTRACE_INFO:
+ return tool->auxtrace_info(tool, event, session);
+ case PERF_RECORD_AUXTRACE:
+ /* setup for reading amidst mmap */
+ lseek(fd, file_offset + event->header.size, SEEK_SET);
+ return tool->auxtrace(tool, event, session);
default:
return -EINVAL;
}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56..0146f8e 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
#include <stdbool.h>
+#include <linux/types.h>
+
struct perf_session;
union perf_event;
struct perf_evlist;
@@ -29,6 +31,9 @@ typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
struct ordered_events *oe);
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+ struct perf_session *session);
+
struct perf_tool {
event_sample sample,
read;
@@ -44,7 +49,9 @@ struct perf_tool {
event_op2 tracing_data;
event_oe finished_round;
event_op2 build_id,
- id_index;
+ id_index,
+ auxtrace_info;
+ event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
};
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 03/44] perf tools: Add user events for AUX area tracing
2015-04-09 15:53 ` [PATCH 03/44] perf tools: Add user events for AUX area tracing Adrian Hunter
@ 2015-04-20 23:06 ` Arnaldo Carvalho de Melo
2015-04-20 23:10 ` Arnaldo Carvalho de Melo
2015-04-21 9:23 ` Adrian Hunter
2015-05-06 2:59 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 2 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-20 23:06 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:43PM +0300, Adrian Hunter escreveu:
> +static int skipn(int fd, off_t n)
> +{
> + char buf[4096];
> + ssize_t ret;
> +
> + while (n > 0) {
> + ret = read(fd, buf, MIN(n, sizeof(buf)));
> + if (ret <= 0)
> + return ret;
> + n -= ret;
> + }
> +
> + return 0;
We have min() in tools/perf/util/include/linux/kernel.h, and that is
what is being used elsewhere in tools/perf/:
[acme@zoo linux]$ find tools/perf/ -name "*.[ch]" | xargs grep '\<min('
| wc -l
20
[acme@zoo linux]$ find tools/perf/ -name "*.[ch]" | xargs grep '\<max('
| wc -l
8
[acme@zoo linux]$
I noticed it tho because of this:
util/session.c: In function ‘skipn’:
util/session.c:279:28: error: comparison between signed and unsigned
integer expressions [-Werror=sign-compare]
ret = read(fd, buf, MIN(n, sizeof(buf)));
^
util/session.c:279:47: error: signed and unsigned type in conditional
expression [-Werror=sign-compare]
ret = read(fd, buf, MIN(n, sizeof(buf)));
^
cc1: all warnings being treated as errors
make[3]: *** [/tmp/build/perf/util/session.o] Error 1
make[3]: *** Waiting for unfinished jobs....
Fixing it to be:
ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
Ok?
- Arnaldo
^ permalink raw reply [flat|nested] 79+ messages in thread* Re: [PATCH 03/44] perf tools: Add user events for AUX area tracing
2015-04-20 23:06 ` Arnaldo Carvalho de Melo
@ 2015-04-20 23:10 ` Arnaldo Carvalho de Melo
2015-04-21 9:23 ` Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-20 23:10 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Mon, Apr 20, 2015 at 08:06:45PM -0300, Arnaldo Carvalho de Melo escreveu:
> I noticed it tho because of this:
>
> util/session.c: In function ‘skipn’:
> util/session.c:279:28: error: comparison between signed and unsigned
> integer expressions [-Werror=sign-compare]
> ret = read(fd, buf, MIN(n, sizeof(buf)));
> ^
> util/session.c:279:47: error: signed and unsigned type in conditional
> expression [-Werror=sign-compare]
> ret = read(fd, buf, MIN(n, sizeof(buf)));
> ^
> cc1: all warnings being treated as errors
> make[3]: *** [/tmp/build/perf/util/session.o] Error 1
> make[3]: *** Waiting for unfinished jobs....
>
> Fixing it to be:
>
> ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
>
> Ok?
I think the right thing would be for us to adopt min_t() and friends, as
defined in include/linux/kernel.h, but will leave this for later...
- Arnaldo
^ permalink raw reply [flat|nested] 79+ messages in thread
* Re: [PATCH 03/44] perf tools: Add user events for AUX area tracing
2015-04-20 23:06 ` Arnaldo Carvalho de Melo
2015-04-20 23:10 ` Arnaldo Carvalho de Melo
@ 2015-04-21 9:23 ` Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-21 9:23 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
On 21/04/15 02:06, Arnaldo Carvalho de Melo wrote:
> Em Thu, Apr 09, 2015 at 06:53:43PM +0300, Adrian Hunter escreveu:
>> +static int skipn(int fd, off_t n)
>> +{
>> + char buf[4096];
>> + ssize_t ret;
>> +
>> + while (n > 0) {
>> + ret = read(fd, buf, MIN(n, sizeof(buf)));
>> + if (ret <= 0)
>> + return ret;
>> + n -= ret;
>> + }
>> +
>> + return 0;
>
> We have min() in tools/perf/util/include/linux/kernel.h, and that is
> what is being used elsewhere in tools/perf/:
>
> [acme@zoo linux]$ find tools/perf/ -name "*.[ch]" | xargs grep '\<min('
> | wc -l
> 20
> [acme@zoo linux]$ find tools/perf/ -name "*.[ch]" | xargs grep '\<max('
> | wc -l
> 8
> [acme@zoo linux]$
>
> I noticed it tho because of this:
>
> util/session.c: In function ‘skipn’:
> util/session.c:279:28: error: comparison between signed and unsigned
> integer expressions [-Werror=sign-compare]
> ret = read(fd, buf, MIN(n, sizeof(buf)));
> ^
> util/session.c:279:47: error: signed and unsigned type in conditional
> expression [-Werror=sign-compare]
> ret = read(fd, buf, MIN(n, sizeof(buf)));
> ^
> cc1: all warnings being treated as errors
> make[3]: *** [/tmp/build/perf/util/session.o] Error 1
> make[3]: *** Waiting for unfinished jobs....
>
> Fixing it to be:
>
> ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
>
> Ok?
Yes, thank you!
There were 3 more patches using MIN so I have fixed and re-sent them.
^ permalink raw reply [flat|nested] 79+ messages in thread
* [tip:perf/core] perf tools: Add user events for AUX area tracing
2015-04-09 15:53 ` [PATCH 03/44] perf tools: Add user events for AUX area tracing Adrian Hunter
2015-04-20 23:06 ` Arnaldo Carvalho de Melo
@ 2015-05-06 2:59 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:59 UTC (permalink / raw)
To: linux-tip-commits
Cc: hpa, linux-kernel, namhyung, adrian.hunter, mingo, peterz, tglx,
jolsa, fweisbec, acme, eranian, dsahern
Commit-ID: a16ac0233ea1da8af3c2046a67c2527b4a452166
Gitweb: http://git.kernel.org/tip/a16ac0233ea1da8af3c2046a67c2527b4a452166
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:43 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:50 -0300
perf tools: Add user events for AUX area tracing
Add two user events for AUX area tracing.
PERF_RECORD_AUXTRACE_INFO contains metadata, consisting primarily the
type of the AUX area tracing data plus some amount of
architecture-specific information. There should be only one
PERF_RECORD_AUXTRACE_INFO event.
PERF_RECORD_AUXTRACE identifies AUX area tracing data copied from the
mmapped AUX area tracing region. The actual data is not part of the
event but immediately follows it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-4-git-send-email-adrian.hunter@intel.com
[ s/MIN/min/g and use cast to fix up wrt -Werror=sign-compare till we adopt min_t() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/event.c | 2 ++
tools/perf/util/event.h | 22 +++++++++++++++
tools/perf/util/session.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/tool.h | 9 ++++++-
4 files changed, 101 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4..adada16 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -29,6 +29,8 @@ static const char *perf_event__names[] = {
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
+ [PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
+ [PERF_RECORD_AUXTRACE] = "AUXTRACE",
};
const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d..6d81bec 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -215,6 +215,8 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_FINISHED_ROUND = 68,
PERF_RECORD_ID_INDEX = 69,
+ PERF_RECORD_AUXTRACE_INFO = 70,
+ PERF_RECORD_AUXTRACE = 71,
PERF_RECORD_HEADER_MAX
};
@@ -280,6 +282,24 @@ struct id_index_event {
struct id_index_entry entries[0];
};
+struct auxtrace_info_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 reserved__; /* For alignment */
+ u64 priv[];
+};
+
+struct auxtrace_event {
+ struct perf_event_header header;
+ u64 size;
+ u64 offset;
+ u64 reference;
+ u32 idx;
+ u32 tid;
+ u32 cpu;
+ u32 reserved__; /* For alignment */
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -295,6 +315,8 @@ union perf_event {
struct tracing_data_event tracing_data;
struct build_id_event build_id;
struct id_index_event id_index;
+ struct auxtrace_info_event auxtrace_info;
+ struct auxtrace_event auxtrace;
};
void perf_event__print_totals(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c74012..d46ac40 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -262,6 +262,40 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
return 0;
}
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+ char buf[4096];
+ ssize_t ret;
+
+ while (n > 0) {
+ ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+ if (ret <= 0)
+ return ret;
+ n -= ret;
+ }
+
+ return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ if (perf_data_file__is_pipe(session->file))
+ skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+ return event->auxtrace.size;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@@ -298,6 +332,10 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
}
if (tool->id_index == NULL)
tool->id_index = process_id_index_stub;
+ if (tool->auxtrace_info == NULL)
+ tool->auxtrace_info = process_event_auxtrace_info_stub;
+ if (tool->auxtrace == NULL)
+ tool->auxtrace = process_event_auxtrace_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@@ -478,6 +516,29 @@ static void perf_event__tracing_data_swap(union perf_event *event,
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ size_t size;
+
+ event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+ size = event->header.size;
+ size -= (void *)&event->auxtrace_info.priv - (void *)event;
+ mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace.size = bswap_64(event->auxtrace.size);
+ event->auxtrace.offset = bswap_64(event->auxtrace.offset);
+ event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+ event->auxtrace.idx = bswap_32(event->auxtrace.idx);
+ event->auxtrace.tid = bswap_32(event->auxtrace.tid);
+ event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@@ -497,6 +558,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
[PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
+ [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
+ [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -980,6 +1043,12 @@ static s64 perf_session__process_user_event(struct perf_session *session,
return tool->finished_round(tool, event, oe);
case PERF_RECORD_ID_INDEX:
return tool->id_index(tool, event, session);
+ case PERF_RECORD_AUXTRACE_INFO:
+ return tool->auxtrace_info(tool, event, session);
+ case PERF_RECORD_AUXTRACE:
+ /* setup for reading amidst mmap */
+ lseek(fd, file_offset + event->header.size, SEEK_SET);
+ return tool->auxtrace(tool, event, session);
default:
return -EINVAL;
}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56..0146f8e 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
#include <stdbool.h>
+#include <linux/types.h>
+
struct perf_session;
union perf_event;
struct perf_evlist;
@@ -29,6 +31,9 @@ typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
struct ordered_events *oe);
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+ struct perf_session *session);
+
struct perf_tool {
event_sample sample,
read;
@@ -44,7 +49,9 @@ struct perf_tool {
event_op2 tracing_data;
event_oe finished_round;
event_op2 build_id,
- id_index;
+ id_index,
+ auxtrace_info;
+ event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
};
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 04/44] perf tools: Add support for AUX area recording
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (2 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 03/44] perf tools: Add user events for AUX area tracing Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-20 23:17 ` Arnaldo Carvalho de Melo
2015-05-06 2:59 ` [tip:perf/core] perf auxtrace: " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 05/44] perf record: Add basic AUX area tracing support Adrian Hunter
` (39 subsequent siblings)
43 siblings, 2 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for reading from the AUX area
tracing mmap and synthesizing AUX area
tracing events.
This patch introduces an abstraction for recording
AUX area data. Recording is initialized
by auxtrace_record__init() which is a weak function
to be implemented by the architecture to provide
recording callbacks. Recording is mainly handled
by auxtrace_mmap__read() and
perf_event__synthesize_auxtrace() but there are
callbacks for miscellaneous needs including
validating and processing user options, populating
private data in auxtrace_info_event, and freeing
the structure when finished.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/perf.h | 2 +
tools/perf/util/auxtrace.c | 176 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 56 ++++++++++++++-
tools/perf/util/record.c | 11 ++-
4 files changed, 243 insertions(+), 2 deletions(-)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb63..5042093 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,8 +54,10 @@ struct record_opts {
bool period;
bool sample_intr_regs;
bool running_time;
+ bool full_auxtrace;
unsigned int freq;
unsigned int mmap_pages;
+ unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 default_interval;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index dedb646..2cafea2 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -23,6 +23,10 @@
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
#include "../perf.h"
#include "util.h"
#include "evlist.h"
@@ -31,6 +35,9 @@
#include "asm/bug.h"
#include "auxtrace.h"
+#include "event.h"
+#include "debug.h"
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
@@ -111,3 +118,172 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
mp->tid = evlist->threads->map[idx];
}
}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->info_priv_size(itr);
+ return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+ pr_err("AUX area tracing is not supported on this architecture\n");
+ return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ if (itr)
+ return itr->info_fill(itr, session, auxtrace_info, priv_size);
+ return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+ if (itr)
+ itr->free(itr);
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ if (itr)
+ return itr->recording_options(itr, evlist, opts);
+ return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->reference(itr);
+ return 0;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+ *err = 0;
+ return NULL;
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process)
+{
+ union perf_event *ev;
+ size_t priv_size;
+ int err;
+
+ pr_debug2("Synthesizing auxtrace information\n");
+ priv_size = auxtrace_record__info_priv_size(itr);
+ ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+ if (!ev)
+ return -ENOMEM;
+
+ ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+ ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+ priv_size;
+ err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+ priv_size);
+ if (err)
+ goto out_free;
+
+ err = process(tool, ev, NULL, NULL);
+out_free:
+ free(ev);
+ return err;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn)
+{
+ u64 head = auxtrace_mmap__read_head(mm);
+ u64 old = mm->prev, offset, ref;
+ unsigned char *data = mm->base;
+ size_t size, head_off, old_off, len1, len2, padding;
+ union perf_event ev;
+ void *data1, *data2;
+
+ if (old == head)
+ return 0;
+
+ pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+ mm->idx, old, head, head - old);
+
+ if (mm->mask) {
+ head_off = head & mm->mask;
+ old_off = old & mm->mask;
+ } else {
+ head_off = head % mm->len;
+ old_off = old % mm->len;
+ }
+
+ if (head_off > old_off)
+ size = head_off - old_off;
+ else
+ size = mm->len - (old_off - head_off);
+
+ ref = auxtrace_record__reference(itr);
+
+ if (head > old || size <= head || mm->mask) {
+ offset = head - size;
+ } else {
+ /*
+ * When the buffer size is not a power of 2, 'head' wraps at the
+ * highest multiple of the buffer size, so we have to subtract
+ * the remainder here.
+ */
+ u64 rem = (0ULL - mm->len) % mm->len;
+
+ offset = head - size - rem;
+ }
+
+ if (size > head_off) {
+ len1 = size - head_off;
+ data1 = &data[mm->len - len1];
+ len2 = head_off;
+ data2 = &data[0];
+ } else {
+ len1 = size;
+ data1 = &data[head_off - len1];
+ len2 = 0;
+ data2 = NULL;
+ }
+
+ /* padding must be written by fn() e.g. record__process_auxtrace() */
+ padding = size & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+ ev.auxtrace.header.size = sizeof(ev.auxtrace);
+ ev.auxtrace.size = size + padding;
+ ev.auxtrace.offset = offset;
+ ev.auxtrace.reference = ref;
+ ev.auxtrace.idx = mm->idx;
+ ev.auxtrace.tid = mm->tid;
+ ev.auxtrace.cpu = mm->cpu;
+
+ if (fn(tool, &ev, data1, len1, data2, len2))
+ return -1;
+
+ mm->prev = head;
+
+ auxtrace_mmap__write_tail(mm, head);
+ if (itr->read_finish) {
+ int err;
+
+ err = itr->read_finish(itr, mm->idx);
+ if (err < 0)
+ return err;
+ }
+
+ return 1;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 2071b36..7ab4850 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -18,13 +18,18 @@
#include <sys/types.h>
#include <stdbool.h>
-
+#include <stddef.h>
#include <linux/perf_event.h>
#include <linux/types.h>
#include "../perf.h"
+union perf_event;
+struct perf_session;
struct perf_evlist;
+struct perf_tool;
+struct record_opts;
+struct auxtrace_info_event;
/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
@@ -70,6 +75,29 @@ struct auxtrace_mmap_params {
int cpu;
};
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+ int (*recording_options)(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+ size_t (*info_priv_size)(struct auxtrace_record *itr);
+ int (*info_fill)(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+ void (*free)(struct auxtrace_record *itr);
+ u64 (*reference)(struct auxtrace_record *itr);
+ int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->userpg;
@@ -114,4 +142,30 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
struct perf_evlist *evlist, int idx,
bool per_cpu);
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+ int *err);
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process);
+
#endif
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df..0ccfa49 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
evsel->attr.comm_exec = 1;
}
- if (evlist->nr_entries > 1) {
+ if (opts->full_auxtrace) {
+ /*
+ * Need to be able to synthesize and parse selected events with
+ * arbitrary sample types, which requires always being able to
+ * match the id.
+ */
+ use_sample_identifier = perf_can_sample_identifier();
+ evlist__for_each(evlist, evsel)
+ perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ } else if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
evlist__for_each(evlist, evsel) {
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 04/44] perf tools: Add support for AUX area recording
2015-04-09 15:53 ` [PATCH 04/44] perf tools: Add support for AUX area recording Adrian Hunter
@ 2015-04-20 23:17 ` Arnaldo Carvalho de Melo
2015-05-06 2:59 ` [tip:perf/core] perf auxtrace: " tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-20 23:17 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:44PM +0300, Adrian Hunter escreveu:
> Add support for reading from the AUX area
> tracing mmap and synthesizing AUX area
> tracing events.
>
> This patch introduces an abstraction for recording
> AUX area data. Recording is initialized
> by auxtrace_record__init() which is a weak function
> to be implemented by the architecture to provide
> recording callbacks. Recording is mainly handled
> by auxtrace_mmap__read() and
> perf_event__synthesize_auxtrace() but there are
> callbacks for miscellaneous needs including
> validating and processing user options, populating
> private data in auxtrace_info_event, and freeing
> the structure when finished.
>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Acked-by: Jiri Olsa <jolsa@kernel.org>
> ---
> tools/perf/perf.h | 2 +
> tools/perf/util/auxtrace.c | 176 +++++++++++++++++++++++++++++++++++++++++++++
> tools/perf/util/auxtrace.h | 56 ++++++++++++++-
> tools/perf/util/record.c | 11 ++-
> 4 files changed, 243 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/perf.h b/tools/perf/perf.h
> index e14bb63..5042093 100644
> --- a/tools/perf/perf.h
> +++ b/tools/perf/perf.h
> @@ -54,8 +54,10 @@ struct record_opts {
> bool period;
> bool sample_intr_regs;
> bool running_time;
> + bool full_auxtrace;
> unsigned int freq;
> unsigned int mmap_pages;
> + unsigned int auxtrace_mmap_pages;
> unsigned int user_freq;
> u64 branch_stack;
> u64 default_interval;
> diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
> index dedb646..2cafea2 100644
> --- a/tools/perf/util/auxtrace.c
> +++ b/tools/perf/util/auxtrace.c
> @@ -23,6 +23,10 @@
> #include <linux/bitops.h>
> #include <linux/log2.h>
>
> +#include <stdlib.h>
> +#include <string.h>
> +#include <errno.h>
> +
> #include "../perf.h"
> #include "util.h"
> #include "evlist.h"
> @@ -31,6 +35,9 @@
> #include "asm/bug.h"
> #include "auxtrace.h"
>
> +#include "event.h"
> +#include "debug.h"
> +
> int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
> struct auxtrace_mmap_params *mp,
> void *userpg, int fd)
> @@ -111,3 +118,172 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
> mp->tid = evlist->threads->map[idx];
> }
> }
> +
> +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
> +{
> + if (itr)
> + return itr->info_priv_size(itr);
> + return 0;
> +}
return itr ? itr->info_priv_size(itr) : 0;
Is more compact, applying anyway... There is one other comment below,
but it is as well cosmetic.
- Arnaldo
> +
> +static int auxtrace_not_supported(void)
> +{
> + pr_err("AUX area tracing is not supported on this architecture\n");
> + return -EINVAL;
> +}
> +
> +int auxtrace_record__info_fill(struct auxtrace_record *itr,
> + struct perf_session *session,
> + struct auxtrace_info_event *auxtrace_info,
> + size_t priv_size)
> +{
> + if (itr)
> + return itr->info_fill(itr, session, auxtrace_info, priv_size);
> + return auxtrace_not_supported();
> +}
> +
> +void auxtrace_record__free(struct auxtrace_record *itr)
> +{
> + if (itr)
> + itr->free(itr);
> +}
> +
> +int auxtrace_record__options(struct auxtrace_record *itr,
> + struct perf_evlist *evlist,
> + struct record_opts *opts)
> +{
> + if (itr)
> + return itr->recording_options(itr, evlist, opts);
> + return 0;
> +}
> +
> +u64 auxtrace_record__reference(struct auxtrace_record *itr)
> +{
> + if (itr)
> + return itr->reference(itr);
> + return 0;
> +}
> +
> +struct auxtrace_record *__weak
> +auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
> +{
> + *err = 0;
> + return NULL;
> +}
> +
> +int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
> + struct perf_tool *tool,
> + struct perf_session *session,
> + perf_event__handler_t process)
> +{
> + union perf_event *ev;
> + size_t priv_size;
> + int err;
> +
> + pr_debug2("Synthesizing auxtrace information\n");
> + priv_size = auxtrace_record__info_priv_size(itr);
> + ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
> + if (!ev)
> + return -ENOMEM;
> +
> + ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
> + ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
> + priv_size;
> + err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
> + priv_size);
> + if (err)
> + goto out_free;
> +
> + err = process(tool, ev, NULL, NULL);
> +out_free:
if (!err)
err = process(tool, ev, NULL, NULL);
> + free(ev);
> + return err;
I.e. I love gotos, but this one isn't needed :-)
> +}
> +
> +int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
> + struct perf_tool *tool, process_auxtrace_t fn)
> +{
> + u64 head = auxtrace_mmap__read_head(mm);
> + u64 old = mm->prev, offset, ref;
> + unsigned char *data = mm->base;
> + size_t size, head_off, old_off, len1, len2, padding;
> + union perf_event ev;
> + void *data1, *data2;
> +
> + if (old == head)
> + return 0;
> +
> + pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
> + mm->idx, old, head, head - old);
> +
> + if (mm->mask) {
> + head_off = head & mm->mask;
> + old_off = old & mm->mask;
> + } else {
> + head_off = head % mm->len;
> + old_off = old % mm->len;
> + }
> +
> + if (head_off > old_off)
> + size = head_off - old_off;
> + else
> + size = mm->len - (old_off - head_off);
> +
> + ref = auxtrace_record__reference(itr);
> +
> + if (head > old || size <= head || mm->mask) {
> + offset = head - size;
> + } else {
> + /*
> + * When the buffer size is not a power of 2, 'head' wraps at the
> + * highest multiple of the buffer size, so we have to subtract
> + * the remainder here.
> + */
> + u64 rem = (0ULL - mm->len) % mm->len;
> +
> + offset = head - size - rem;
> + }
> +
> + if (size > head_off) {
> + len1 = size - head_off;
> + data1 = &data[mm->len - len1];
> + len2 = head_off;
> + data2 = &data[0];
> + } else {
> + len1 = size;
> + data1 = &data[head_off - len1];
> + len2 = 0;
> + data2 = NULL;
> + }
> +
> + /* padding must be written by fn() e.g. record__process_auxtrace() */
> + padding = size & 7;
> + if (padding)
> + padding = 8 - padding;
> +
> + memset(&ev, 0, sizeof(ev));
> + ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
> + ev.auxtrace.header.size = sizeof(ev.auxtrace);
> + ev.auxtrace.size = size + padding;
> + ev.auxtrace.offset = offset;
> + ev.auxtrace.reference = ref;
> + ev.auxtrace.idx = mm->idx;
> + ev.auxtrace.tid = mm->tid;
> + ev.auxtrace.cpu = mm->cpu;
> +
> + if (fn(tool, &ev, data1, len1, data2, len2))
> + return -1;
> +
> + mm->prev = head;
> +
> + auxtrace_mmap__write_tail(mm, head);
> + if (itr->read_finish) {
> + int err;
> +
> + err = itr->read_finish(itr, mm->idx);
> + if (err < 0)
> + return err;
> + }
> +
> + return 1;
> +}
> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
> index 2071b36..7ab4850 100644
> --- a/tools/perf/util/auxtrace.h
> +++ b/tools/perf/util/auxtrace.h
> @@ -18,13 +18,18 @@
>
> #include <sys/types.h>
> #include <stdbool.h>
> -
> +#include <stddef.h>
> #include <linux/perf_event.h>
> #include <linux/types.h>
>
> #include "../perf.h"
>
> +union perf_event;
> +struct perf_session;
> struct perf_evlist;
> +struct perf_tool;
> +struct record_opts;
> +struct auxtrace_info_event;
>
> /**
> * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
> @@ -70,6 +75,29 @@ struct auxtrace_mmap_params {
> int cpu;
> };
>
> +/**
> + * struct auxtrace_record - callbacks for recording AUX area data.
> + * @recording_options: validate and process recording options
> + * @info_priv_size: return the size of the private data in auxtrace_info_event
> + * @info_fill: fill-in the private data in auxtrace_info_event
> + * @free: free this auxtrace record structure
> + * @reference: provide a 64-bit reference number for auxtrace_event
> + * @read_finish: called after reading from an auxtrace mmap
> + */
> +struct auxtrace_record {
> + int (*recording_options)(struct auxtrace_record *itr,
> + struct perf_evlist *evlist,
> + struct record_opts *opts);
> + size_t (*info_priv_size)(struct auxtrace_record *itr);
> + int (*info_fill)(struct auxtrace_record *itr,
> + struct perf_session *session,
> + struct auxtrace_info_event *auxtrace_info,
> + size_t priv_size);
> + void (*free)(struct auxtrace_record *itr);
> + u64 (*reference)(struct auxtrace_record *itr);
> + int (*read_finish)(struct auxtrace_record *itr, int idx);
> +};
> +
> static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
> {
> struct perf_event_mmap_page *pc = mm->userpg;
> @@ -114,4 +142,30 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
> struct perf_evlist *evlist, int idx,
> bool per_cpu);
>
> +typedef int (*process_auxtrace_t)(struct perf_tool *tool,
> + union perf_event *event, void *data1,
> + size_t len1, void *data2, size_t len2);
> +
> +int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
> + struct perf_tool *tool, process_auxtrace_t fn);
> +
> +struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
> + int *err);
> +
> +int auxtrace_record__options(struct auxtrace_record *itr,
> + struct perf_evlist *evlist,
> + struct record_opts *opts);
> +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
> +int auxtrace_record__info_fill(struct auxtrace_record *itr,
> + struct perf_session *session,
> + struct auxtrace_info_event *auxtrace_info,
> + size_t priv_size);
> +void auxtrace_record__free(struct auxtrace_record *itr);
> +u64 auxtrace_record__reference(struct auxtrace_record *itr);
> +
> +int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
> + struct perf_tool *tool,
> + struct perf_session *session,
> + perf_event__handler_t process);
> +
> #endif
> diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
> index 8acd0df..0ccfa49 100644
> --- a/tools/perf/util/record.c
> +++ b/tools/perf/util/record.c
> @@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
> evsel->attr.comm_exec = 1;
> }
>
> - if (evlist->nr_entries > 1) {
> + if (opts->full_auxtrace) {
> + /*
> + * Need to be able to synthesize and parse selected events with
> + * arbitrary sample types, which requires always being able to
> + * match the id.
> + */
> + use_sample_identifier = perf_can_sample_identifier();
> + evlist__for_each(evlist, evsel)
> + perf_evsel__set_sample_id(evsel, use_sample_identifier);
> + } else if (evlist->nr_entries > 1) {
> struct perf_evsel *first = perf_evlist__first(evlist);
>
> evlist__for_each(evlist, evsel) {
> --
> 1.9.1
^ permalink raw reply [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add support for AUX area recording
2015-04-09 15:53 ` [PATCH 04/44] perf tools: Add support for AUX area recording Adrian Hunter
2015-04-20 23:17 ` Arnaldo Carvalho de Melo
@ 2015-05-06 2:59 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:59 UTC (permalink / raw)
To: linux-tip-commits
Cc: fweisbec, dsahern, mingo, acme, jolsa, eranian, linux-kernel,
hpa, peterz, namhyung, adrian.hunter, tglx
Commit-ID: 9e0cc4fe3752661220ee2cf7fcd335e233eea470
Gitweb: http://git.kernel.org/tip/9e0cc4fe3752661220ee2cf7fcd335e233eea470
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:44 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:51 -0300
perf auxtrace: Add support for AUX area recording
Add support for reading from the AUX area tracing mmap and synthesizing
AUX area tracing events.
This patch introduces an abstraction for recording AUX area data.
Recording is initialized by auxtrace_record__init() which is a weak
function to be implemented by the architecture to provide recording
callbacks.
Recording is mainly handled by auxtrace_mmap__read() and
perf_event__synthesize_auxtrace() but there are callbacks for
miscellaneous needs including validating and processing user options,
populating private data in auxtrace_info_event, and freeing the
structure when finished.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/perf.h | 2 +
tools/perf/util/auxtrace.c | 176 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 56 ++++++++++++++-
tools/perf/util/record.c | 11 ++-
4 files changed, 243 insertions(+), 2 deletions(-)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb63..5042093 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,8 +54,10 @@ struct record_opts {
bool period;
bool sample_intr_regs;
bool running_time;
+ bool full_auxtrace;
unsigned int freq;
unsigned int mmap_pages;
+ unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 default_interval;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index dedb646..2cafea2 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -23,6 +23,10 @@
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
#include "../perf.h"
#include "util.h"
#include "evlist.h"
@@ -31,6 +35,9 @@
#include "asm/bug.h"
#include "auxtrace.h"
+#include "event.h"
+#include "debug.h"
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
@@ -111,3 +118,172 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
mp->tid = evlist->threads->map[idx];
}
}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->info_priv_size(itr);
+ return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+ pr_err("AUX area tracing is not supported on this architecture\n");
+ return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ if (itr)
+ return itr->info_fill(itr, session, auxtrace_info, priv_size);
+ return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+ if (itr)
+ itr->free(itr);
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ if (itr)
+ return itr->recording_options(itr, evlist, opts);
+ return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->reference(itr);
+ return 0;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+ *err = 0;
+ return NULL;
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process)
+{
+ union perf_event *ev;
+ size_t priv_size;
+ int err;
+
+ pr_debug2("Synthesizing auxtrace information\n");
+ priv_size = auxtrace_record__info_priv_size(itr);
+ ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+ if (!ev)
+ return -ENOMEM;
+
+ ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+ ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+ priv_size;
+ err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+ priv_size);
+ if (err)
+ goto out_free;
+
+ err = process(tool, ev, NULL, NULL);
+out_free:
+ free(ev);
+ return err;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn)
+{
+ u64 head = auxtrace_mmap__read_head(mm);
+ u64 old = mm->prev, offset, ref;
+ unsigned char *data = mm->base;
+ size_t size, head_off, old_off, len1, len2, padding;
+ union perf_event ev;
+ void *data1, *data2;
+
+ if (old == head)
+ return 0;
+
+ pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+ mm->idx, old, head, head - old);
+
+ if (mm->mask) {
+ head_off = head & mm->mask;
+ old_off = old & mm->mask;
+ } else {
+ head_off = head % mm->len;
+ old_off = old % mm->len;
+ }
+
+ if (head_off > old_off)
+ size = head_off - old_off;
+ else
+ size = mm->len - (old_off - head_off);
+
+ ref = auxtrace_record__reference(itr);
+
+ if (head > old || size <= head || mm->mask) {
+ offset = head - size;
+ } else {
+ /*
+ * When the buffer size is not a power of 2, 'head' wraps at the
+ * highest multiple of the buffer size, so we have to subtract
+ * the remainder here.
+ */
+ u64 rem = (0ULL - mm->len) % mm->len;
+
+ offset = head - size - rem;
+ }
+
+ if (size > head_off) {
+ len1 = size - head_off;
+ data1 = &data[mm->len - len1];
+ len2 = head_off;
+ data2 = &data[0];
+ } else {
+ len1 = size;
+ data1 = &data[head_off - len1];
+ len2 = 0;
+ data2 = NULL;
+ }
+
+ /* padding must be written by fn() e.g. record__process_auxtrace() */
+ padding = size & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+ ev.auxtrace.header.size = sizeof(ev.auxtrace);
+ ev.auxtrace.size = size + padding;
+ ev.auxtrace.offset = offset;
+ ev.auxtrace.reference = ref;
+ ev.auxtrace.idx = mm->idx;
+ ev.auxtrace.tid = mm->tid;
+ ev.auxtrace.cpu = mm->cpu;
+
+ if (fn(tool, &ev, data1, len1, data2, len2))
+ return -1;
+
+ mm->prev = head;
+
+ auxtrace_mmap__write_tail(mm, head);
+ if (itr->read_finish) {
+ int err;
+
+ err = itr->read_finish(itr, mm->idx);
+ if (err < 0)
+ return err;
+ }
+
+ return 1;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 2071b36..7ab4850 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -18,13 +18,18 @@
#include <sys/types.h>
#include <stdbool.h>
-
+#include <stddef.h>
#include <linux/perf_event.h>
#include <linux/types.h>
#include "../perf.h"
+union perf_event;
+struct perf_session;
struct perf_evlist;
+struct perf_tool;
+struct record_opts;
+struct auxtrace_info_event;
/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
@@ -70,6 +75,29 @@ struct auxtrace_mmap_params {
int cpu;
};
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+ int (*recording_options)(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+ size_t (*info_priv_size)(struct auxtrace_record *itr);
+ int (*info_fill)(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+ void (*free)(struct auxtrace_record *itr);
+ u64 (*reference)(struct auxtrace_record *itr);
+ int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->userpg;
@@ -114,4 +142,30 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
struct perf_evlist *evlist, int idx,
bool per_cpu);
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+ int *err);
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process);
+
#endif
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df..0ccfa49 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
evsel->attr.comm_exec = 1;
}
- if (evlist->nr_entries > 1) {
+ if (opts->full_auxtrace) {
+ /*
+ * Need to be able to synthesize and parse selected events with
+ * arbitrary sample types, which requires always being able to
+ * match the id.
+ */
+ use_sample_identifier = perf_can_sample_identifier();
+ evlist__for_each(evlist, evsel)
+ perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ } else if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
evlist__for_each(evlist, evsel) {
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 05/44] perf record: Add basic AUX area tracing support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (3 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 04/44] perf tools: Add support for AUX area recording Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 2:59 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 06/44] perf record: Extend -m option for AUX area tracing mmap pages Adrian Hunter
` (38 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Amend the perf record tool to read the
AUX area tracing mmap and synthesize
AUX area tracing events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/builtin-record.c | 81 ++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 77 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ac61048..8879efe 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,6 +27,7 @@
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <unistd.h>
#include <sched.h>
@@ -38,6 +39,7 @@ struct record {
struct record_opts opts;
u64 bytes_written;
struct perf_data_file file;
+ struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
@@ -110,6 +112,44 @@ out:
return rc;
}
+static int record__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2)
+{
+ struct record *rec = container_of(tool, struct record, tool);
+ size_t padding;
+ u8 pad[8] = {0};
+
+ /* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+ padding = (len1 + len2) & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ record__write(rec, event, event->header.size);
+ record__write(rec, data1, len1);
+ if (len2)
+ record__write(rec, data2, len2);
+ record__write(rec, &pad, padding);
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+ record__process_auxtrace);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
@@ -169,13 +209,15 @@ try_again:
goto out;
}
- if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+ if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+ opts->auxtrace_mmap_pages, false) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
- "(current value: %u)\n", opts->mmap_pages);
+ "(current value: %u,%u)\n",
+ opts->mmap_pages, opts->auxtrace_mmap_pages);
rc = -errno;
} else {
pr_err("failed to mmap with %d (%s)\n", errno,
@@ -270,12 +312,20 @@ static int record__mmap_read_all(struct record *rec)
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
if (rec->evlist->mmap[i].base) {
if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
+
+ if (mm->base &&
+ record__auxtrace_mmap_read(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
}
/*
@@ -305,6 +355,9 @@ static void record__init_features(struct record *rec)
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+ if (!rec->opts.full_auxtrace)
+ perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static volatile int workload_exec_errno;
@@ -421,6 +474,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}
}
+ if (rec->opts.full_auxtrace) {
+ err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+ session, process_synthesized_event);
+ if (err)
+ goto out_delete_session;
+ }
+
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
if (err < 0)
@@ -553,7 +613,7 @@ out_child:
if (!err && !quiet) {
char samples[128];
- if (rec->samples)
+ if (rec->samples && !rec->opts.full_auxtrace)
scnprintf(samples, sizeof(samples),
" (%" PRIu64 " samples)", rec->samples);
else
@@ -936,7 +996,7 @@ struct option *record_options = __record_options;
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int err = -ENOMEM;
+ int err;
struct record *rec = &record;
char errbuf[BUFSIZ];
@@ -957,6 +1017,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
usage_with_options(record_usage, record_options);
}
+ if (!rec->itr) {
+ rec->itr = auxtrace_record__init(rec->evlist, &err);
+ if (err)
+ return err;
+ }
+
+ err = -ENOMEM;
+
symbol__init(NULL);
if (symbol_conf.kptr_restrict)
@@ -1002,6 +1070,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
+ err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+ if (err)
+ goto out_symbol_exit;
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out_symbol_exit;
@@ -1011,5 +1083,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
out_symbol_exit:
perf_evlist__delete(rec->evlist);
symbol__exit();
+ auxtrace_record__free(rec->itr);
return err;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf record: Add basic AUX area tracing support
2015-04-09 15:53 ` [PATCH 05/44] perf record: Add basic AUX area tracing support Adrian Hunter
@ 2015-05-06 2:59 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:59 UTC (permalink / raw)
To: linux-tip-commits
Cc: adrian.hunter, namhyung, linux-kernel, eranian, dsahern, tglx,
peterz, fweisbec, hpa, jolsa, acme, mingo
Commit-ID: ef149c2548b82e75f7f9d138457ef4dc4ed97448
Gitweb: http://git.kernel.org/tip/ef149c2548b82e75f7f9d138457ef4dc4ed97448
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:45 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:51 -0300
perf record: Add basic AUX area tracing support
Amend the perf record tool to read the AUX area tracing mmap and
synthesize AUX area tracing events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 81 ++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 77 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c3efdfb..0fb11d4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,6 +27,7 @@
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <unistd.h>
#include <sched.h>
@@ -38,6 +39,7 @@ struct record {
struct record_opts opts;
u64 bytes_written;
struct perf_data_file file;
+ struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
@@ -110,6 +112,44 @@ out:
return rc;
}
+static int record__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2)
+{
+ struct record *rec = container_of(tool, struct record, tool);
+ size_t padding;
+ u8 pad[8] = {0};
+
+ /* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+ padding = (len1 + len2) & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ record__write(rec, event, event->header.size);
+ record__write(rec, data1, len1);
+ if (len2)
+ record__write(rec, data2, len2);
+ record__write(rec, &pad, padding);
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+ record__process_auxtrace);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
@@ -169,13 +209,15 @@ try_again:
goto out;
}
- if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+ if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+ opts->auxtrace_mmap_pages, false) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
- "(current value: %u)\n", opts->mmap_pages);
+ "(current value: %u,%u)\n",
+ opts->mmap_pages, opts->auxtrace_mmap_pages);
rc = -errno;
} else {
pr_err("failed to mmap with %d (%s)\n", errno,
@@ -270,12 +312,20 @@ static int record__mmap_read_all(struct record *rec)
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
if (rec->evlist->mmap[i].base) {
if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
+
+ if (mm->base &&
+ record__auxtrace_mmap_read(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
}
/*
@@ -305,6 +355,9 @@ static void record__init_features(struct record *rec)
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+ if (!rec->opts.full_auxtrace)
+ perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static volatile int workload_exec_errno;
@@ -421,6 +474,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}
}
+ if (rec->opts.full_auxtrace) {
+ err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+ session, process_synthesized_event);
+ if (err)
+ goto out_delete_session;
+ }
+
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
if (err < 0)
@@ -553,7 +613,7 @@ out_child:
if (!err && !quiet) {
char samples[128];
- if (rec->samples)
+ if (rec->samples && !rec->opts.full_auxtrace)
scnprintf(samples, sizeof(samples),
" (%" PRIu64 " samples)", rec->samples);
else
@@ -936,7 +996,7 @@ struct option *record_options = __record_options;
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int err = -ENOMEM;
+ int err;
struct record *rec = &record;
char errbuf[BUFSIZ];
@@ -957,6 +1017,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
usage_with_options(record_usage, record_options);
}
+ if (!rec->itr) {
+ rec->itr = auxtrace_record__init(rec->evlist, &err);
+ if (err)
+ return err;
+ }
+
+ err = -ENOMEM;
+
symbol__init(NULL);
if (symbol_conf.kptr_restrict)
@@ -1002,6 +1070,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
+ err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+ if (err)
+ goto out_symbol_exit;
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out_symbol_exit;
@@ -1011,5 +1083,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
out_symbol_exit:
perf_evlist__delete(rec->evlist);
symbol__exit();
+ auxtrace_record__free(rec->itr);
return err;
}
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 06/44] perf record: Extend -m option for AUX area tracing mmap pages
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (4 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 05/44] perf record: Add basic AUX area tracing support Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 2:59 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 07/44] perf tools: Add a user event for AUX area tracing errors Adrian Hunter
` (37 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Extend the -m option so that the number
of mmap pages for AUX area tracing
can be specified by adding a comma followed
by the number of pages.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/Documentation/perf-record.txt | 2 ++
tools/perf/builtin-record.c | 49 ++++++++++++++++++++++++++++++--
tools/perf/util/evlist.c | 10 +++++--
tools/perf/util/evlist.h | 1 +
4 files changed, 56 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 4847a79..76a141e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,8 @@ OPTIONS
Number of mmap data pages (must be a power of two) or size
specification with appended unit character - B/K/M/G. The
size is rounded up to have nearest pages power of two value.
+ Also, by adding a comma, the number of mmap pages for AUX
+ area tracing can be specified.
--group::
Put all events in a single event group. This precedes the --event
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8879efe..009ec31 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -855,6 +855,49 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
return -1;
}
+static int record__parse_mmap_pages(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *s, *p;
+ unsigned int mmap_pages;
+ int ret;
+
+ if (!str)
+ return -EINVAL;
+
+ s = strdup(str);
+ if (!s)
+ return -ENOMEM;
+
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ if (*s) {
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+ if (ret)
+ goto out_free;
+ opts->mmap_pages = mmap_pages;
+ }
+
+ if (!p) {
+ ret = 0;
+ goto out_free;
+ }
+
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+ if (ret)
+ goto out_free;
+
+ opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+ free(s);
+ return ret;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -935,9 +978,9 @@ struct option __record_options[] = {
&record.opts.no_inherit_set,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
- OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
- "number of mmap data pages",
- perf_evlist__parse_mmap_pages),
+ OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+ "number of mmap data pages and AUX area tracing mmap pages",
+ record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a588e01..e4289e6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1000,10 +1000,8 @@ static long parse_pages_arg(const char *str, unsigned long min,
return pages;
}
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
- int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
{
- unsigned int *mmap_pages = opt->value;
unsigned long max = UINT_MAX;
long pages;
@@ -1020,6 +1018,12 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
return 0;
}
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
/**
* perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index beed571..221ac3d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -124,6 +124,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist);
struct option;
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf record: Extend -m option for AUX area tracing mmap pages
2015-04-09 15:53 ` [PATCH 06/44] perf record: Extend -m option for AUX area tracing mmap pages Adrian Hunter
@ 2015-05-06 2:59 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 2:59 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, namhyung, dsahern, mingo, linux-kernel, acme, fweisbec,
adrian.hunter, tglx, jolsa, hpa, peterz
Commit-ID: e9db1310d95c9d02763643108d51e47d9eb79ac9
Gitweb: http://git.kernel.org/tip/e9db1310d95c9d02763643108d51e47d9eb79ac9
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:46 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:52 -0300
perf record: Extend -m option for AUX area tracing mmap pages
Extend the -m option so that the number of mmap pages for AUX area
tracing can be specified by adding a comma followed by the number of
pages.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-record.txt | 2 ++
tools/perf/builtin-record.c | 49 ++++++++++++++++++++++++++++++--
tools/perf/util/evlist.c | 10 +++++--
tools/perf/util/evlist.h | 1 +
4 files changed, 56 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 4847a79..76a141e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,8 @@ OPTIONS
Number of mmap data pages (must be a power of two) or size
specification with appended unit character - B/K/M/G. The
size is rounded up to have nearest pages power of two value.
+ Also, by adding a comma, the number of mmap pages for AUX
+ area tracing can be specified.
--group::
Put all events in a single event group. This precedes the --event
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0fb11d4..4c9aaa1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -855,6 +855,49 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
return -1;
}
+static int record__parse_mmap_pages(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *s, *p;
+ unsigned int mmap_pages;
+ int ret;
+
+ if (!str)
+ return -EINVAL;
+
+ s = strdup(str);
+ if (!s)
+ return -ENOMEM;
+
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ if (*s) {
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+ if (ret)
+ goto out_free;
+ opts->mmap_pages = mmap_pages;
+ }
+
+ if (!p) {
+ ret = 0;
+ goto out_free;
+ }
+
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+ if (ret)
+ goto out_free;
+
+ opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+ free(s);
+ return ret;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -935,9 +978,9 @@ struct option __record_options[] = {
&record.opts.no_inherit_set,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
- OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
- "number of mmap data pages",
- perf_evlist__parse_mmap_pages),
+ OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+ "number of mmap data pages and AUX area tracing mmap pages",
+ record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5b26f45..0ec8c3b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1000,10 +1000,8 @@ static long parse_pages_arg(const char *str, unsigned long min,
return pages;
}
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
- int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
{
- unsigned int *mmap_pages = opt->value;
unsigned long max = UINT_MAX;
long pages;
@@ -1020,6 +1018,12 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
return 0;
}
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
/**
* perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8dc986d..c07b1a9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -124,6 +124,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist);
struct option;
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 07/44] perf tools: Add a user event for AUX area tracing errors
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (5 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 06/44] perf record: Extend -m option for AUX area tracing mmap pages Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:00 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data Adrian Hunter
` (36 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Errors encountered when decoding an AUX area
trace need to be reported to the user. However
the "user" might be a script or another tool,
so provide a new user event to capture those
errors.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/event.c | 1 +
tools/perf/util/event.h | 16 ++++++++++++++++
tools/perf/util/session.c | 25 +++++++++++++++++++++++++
tools/perf/util/tool.h | 3 ++-
4 files changed, 44 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 07186ba..a0c8740 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
[PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
[PERF_RECORD_AUXTRACE] = "AUXTRACE",
+ [PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
};
const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 6d81bec..657dcfa 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -217,6 +217,7 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_ID_INDEX = 69,
PERF_RECORD_AUXTRACE_INFO = 70,
PERF_RECORD_AUXTRACE = 71,
+ PERF_RECORD_AUXTRACE_ERROR = 72,
PERF_RECORD_HEADER_MAX
};
@@ -300,6 +301,20 @@ struct auxtrace_event {
u32 reserved__; /* For alignment */
};
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 code;
+ u32 cpu;
+ u32 pid;
+ u32 tid;
+ u32 reserved__; /* For alignment */
+ u64 ip;
+ char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -317,6 +332,7 @@ union perf_event {
struct id_index_event id_index;
struct auxtrace_info_event auxtrace_info;
struct auxtrace_event auxtrace;
+ struct auxtrace_error_event auxtrace_error;
};
void perf_event__print_totals(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cc78568..18e4034 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -296,6 +296,15 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
return event->auxtrace.size;
}
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@@ -336,6 +345,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->auxtrace_info = process_event_auxtrace_info_stub;
if (tool->auxtrace == NULL)
tool->auxtrace = process_event_auxtrace_stub;
+ if (tool->auxtrace_error == NULL)
+ tool->auxtrace_error = process_event_auxtrace_error_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@@ -539,6 +550,17 @@ static void perf_event__auxtrace_swap(union perf_event *event,
event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
}
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+ event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+ event->auxtrace_error.cpu = bswap_32(event->auxtrace_error.cpu);
+ event->auxtrace_error.pid = bswap_32(event->auxtrace_error.pid);
+ event->auxtrace_error.tid = bswap_32(event->auxtrace_error.tid);
+ event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@@ -560,6 +582,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
[PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
[PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
+ [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -1049,6 +1072,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
/* setup for reading amidst mmap */
lseek(fd, file_offset + event->header.size, SEEK_SET);
return tool->auxtrace(tool, event, session);
+ case PERF_RECORD_AUXTRACE_ERROR:
+ return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 0146f8e..20afe19 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -50,7 +50,8 @@ struct perf_tool {
event_oe finished_round;
event_op2 build_id,
id_index,
- auxtrace_info;
+ auxtrace_info,
+ auxtrace_error;
event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf tools: Add a user event for AUX area tracing errors
2015-04-09 15:53 ` [PATCH 07/44] perf tools: Add a user event for AUX area tracing errors Adrian Hunter
@ 2015-05-06 3:00 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:00 UTC (permalink / raw)
To: linux-tip-commits
Cc: dsahern, fweisbec, eranian, hpa, tglx, jolsa, mingo,
linux-kernel, acme, peterz, namhyung, adrian.hunter
Commit-ID: e9bf54d25f4f64c410c2aca644749a3325b96f5a
Gitweb: http://git.kernel.org/tip/e9bf54d25f4f64c410c2aca644749a3325b96f5a
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:47 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:52 -0300
perf tools: Add a user event for AUX area tracing errors
Errors encountered when decoding an AUX area trace need to be reported
to the user. However the "user" might be a script or another tool, so
provide a new user event to capture those errors.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/event.c | 1 +
tools/perf/util/event.h | 16 ++++++++++++++++
tools/perf/util/session.c | 25 +++++++++++++++++++++++++
tools/perf/util/tool.h | 3 ++-
4 files changed, 44 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index adada16..32323e5 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
[PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
[PERF_RECORD_AUXTRACE] = "AUXTRACE",
+ [PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
};
const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 6d81bec..657dcfa 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -217,6 +217,7 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_ID_INDEX = 69,
PERF_RECORD_AUXTRACE_INFO = 70,
PERF_RECORD_AUXTRACE = 71,
+ PERF_RECORD_AUXTRACE_ERROR = 72,
PERF_RECORD_HEADER_MAX
};
@@ -300,6 +301,20 @@ struct auxtrace_event {
u32 reserved__; /* For alignment */
};
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 code;
+ u32 cpu;
+ u32 pid;
+ u32 tid;
+ u32 reserved__; /* For alignment */
+ u64 ip;
+ char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -317,6 +332,7 @@ union perf_event {
struct id_index_event id_index;
struct auxtrace_info_event auxtrace_info;
struct auxtrace_event auxtrace;
+ struct auxtrace_error_event auxtrace_error;
};
void perf_event__print_totals(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d46ac40..4008dab 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -296,6 +296,15 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
return event->auxtrace.size;
}
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@@ -336,6 +345,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->auxtrace_info = process_event_auxtrace_info_stub;
if (tool->auxtrace == NULL)
tool->auxtrace = process_event_auxtrace_stub;
+ if (tool->auxtrace_error == NULL)
+ tool->auxtrace_error = process_event_auxtrace_error_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@@ -539,6 +550,17 @@ static void perf_event__auxtrace_swap(union perf_event *event,
event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
}
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+ event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+ event->auxtrace_error.cpu = bswap_32(event->auxtrace_error.cpu);
+ event->auxtrace_error.pid = bswap_32(event->auxtrace_error.pid);
+ event->auxtrace_error.tid = bswap_32(event->auxtrace_error.tid);
+ event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@@ -560,6 +582,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
[PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
[PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
+ [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -1049,6 +1072,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
/* setup for reading amidst mmap */
lseek(fd, file_offset + event->header.size, SEEK_SET);
return tool->auxtrace(tool, event, session);
+ case PERF_RECORD_AUXTRACE_ERROR:
+ return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 0146f8e..20afe19 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -50,7 +50,8 @@ struct perf_tool {
event_oe finished_round;
event_op2 build_id,
id_index,
- auxtrace_info;
+ auxtrace_info,
+ auxtrace_error;
event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (6 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 07/44] perf tools: Add a user event for AUX area tracing errors Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-21 14:41 ` Arnaldo Carvalho de Melo
2015-05-06 3:00 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 09/44] perf session: Add instruction tracing options Adrian Hunter
` (35 subsequent siblings)
43 siblings, 2 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Hook into session processing so that AUX area decoding can
synthesize events transparently to the tools.
The advantages of transparent decoding are that tools can be used
directly with perf.data files containing AUX area tracing data,
which is easier for the user and more efficient than having a
separate decoding tool.
This will work as follows:
1. Tools will feed auxtrace events to the decoder using
perf_tool->auxtrace() (support for that still to come).
2. The decoder can process side-band events as needed due
to the auxtrace->process_event() hook.
3. The decoder can deliver synthesized events into the
event stream using perf_session__deliver_synth_event().
Note the expectation is that decoding will work on data that is
time-ordered with respect to the per-cpu or per-thread contexts
that were recorded.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/session.c | 54 ++++++++++++++++++++++++++++++++++++---------
tools/perf/util/session.h | 3 +++
3 files changed, 102 insertions(+), 10 deletions(-)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 7ab4850..199fc27 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include "../perf.h"
+#include "session.h"
union perf_event;
struct perf_session;
@@ -32,6 +33,24 @@ struct record_opts;
struct auxtrace_info_event;
/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+ int (*process_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool);
+ int (*flush_events)(struct perf_session *session,
+ struct perf_tool *tool);
+ void (*free_events)(struct perf_session *session);
+ void (*free)(struct perf_session *session);
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -168,4 +187,40 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_session *session,
perf_event__handler_t process);
+static inline int auxtrace__process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free(session);
+}
+
#endif
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 18e4034..cf9d678 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,13 @@
#include "cpumap.h"
#include "perf_regs.h"
#include "asm/bug.h"
+#include "auxtrace.h"
-static int machines__deliver_event(struct machines *machines,
- struct perf_evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset);
static int perf_session__open(struct perf_session *session)
{
@@ -105,8 +106,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
return ret;
}
- return machines__deliver_event(&session->machines, session->evlist, event->event,
- &sample, session->tool, event->file_offset);
+ return perf_session__deliver_event(session, event->event, &sample,
+ session->tool, event->file_offset);
}
struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -185,6 +186,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
void perf_session__delete(struct perf_session *session)
{
+ auxtrace__free(session);
perf_session__destroy_kernel_maps(session);
perf_session__delete_threads(session);
perf_session_env__delete(&session->header.env);
@@ -1030,6 +1032,24 @@ static int machines__deliver_event(struct machines *machines,
}
}
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset)
+{
+ int ret;
+
+ ret = auxtrace__process_event(session, event, sample, tool);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ return 0;
+
+ return machines__deliver_event(&session->machines, session->evlist,
+ event, sample, tool, file_offset);
+}
+
static s64 perf_session__process_user_event(struct perf_session *session,
union perf_event *event,
u64 file_offset)
@@ -1190,8 +1210,8 @@ static s64 perf_session__process_event(struct perf_session *session,
return ret;
}
- return machines__deliver_event(&session->machines, evlist, event,
- &sample, tool, file_offset);
+ return perf_session__deliver_event(session, event, &sample, tool,
+ file_offset);
}
void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1350,10 +1370,14 @@ more:
done:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
free(buf);
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
return err;
}
@@ -1496,10 +1520,14 @@ more:
out:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
ui_progress__finish();
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
session->one_mmap = false;
return err;
}
@@ -1582,7 +1610,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
{
- size_t ret = fprintf(fp, "Aggregated stats:\n");
+ size_t ret;
+ const char *msg = "";
+
+ if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+ ret = fprintf(fp, "Aggregated stats:%s\n", msg);
ret += events_stats__fprintf(&session->evlist->stats, fp);
return ret;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b791..8a69d3b 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,13 @@
struct ip_callchain;
struct thread;
+struct auxtrace;
+
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
+ struct auxtrace *auxtrace;
struct trace_event tevent;
bool repipe;
bool one_mmap;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data
2015-04-09 15:53 ` [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data Adrian Hunter
@ 2015-04-21 14:41 ` Arnaldo Carvalho de Melo
2015-04-21 14:46 ` Arnaldo Carvalho de Melo
2015-05-06 3:00 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 1 reply; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-21 14:41 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:48PM +0300, Adrian Hunter escreveu:
> Hook into session processing so that AUX area decoding can
> synthesize events transparently to the tools.
>
> The advantages of transparent decoding are that tools can be used
> directly with perf.data files containing AUX area tracing data,
> which is easier for the user and more efficient than having a
> separate decoding tool.
>
> This will work as follows:
> 1. Tools will feed auxtrace events to the decoder using
> perf_tool->auxtrace() (support for that still to come).
> 2. The decoder can process side-band events as needed due
> to the auxtrace->process_event() hook.
> 3. The decoder can deliver synthesized events into the
> event stream using perf_session__deliver_synth_event().
So, here this clashes with work I'm doing to untie ordered_events from
perf_session, undoes it even, trying to decipher if this is really
needed...
- Arnaldo
> Note the expectation is that decoding will work on data that is
> time-ordered with respect to the per-cpu or per-thread contexts
> that were recorded.
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
> tools/perf/util/auxtrace.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
> tools/perf/util/session.c | 54 ++++++++++++++++++++++++++++++++++++---------
> tools/perf/util/session.h | 3 +++
> 3 files changed, 102 insertions(+), 10 deletions(-)
>
> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
> index 7ab4850..199fc27 100644
> --- a/tools/perf/util/auxtrace.h
> +++ b/tools/perf/util/auxtrace.h
> @@ -23,6 +23,7 @@
> #include <linux/types.h>
>
> #include "../perf.h"
> +#include "session.h"
>
> union perf_event;
> struct perf_session;
> @@ -32,6 +33,24 @@ struct record_opts;
> struct auxtrace_info_event;
>
> /**
> + * struct auxtrace - session callbacks to allow AUX area data decoding.
> + * @process_event: lets the decoder see all session events
> + * @flush_events: process any remaining data
> + * @free_events: free resources associated with event processing
> + * @free: free resources associated with the session
> + */
> +struct auxtrace {
> + int (*process_event)(struct perf_session *session,
> + union perf_event *event,
> + struct perf_sample *sample,
> + struct perf_tool *tool);
> + int (*flush_events)(struct perf_session *session,
> + struct perf_tool *tool);
> + void (*free_events)(struct perf_session *session);
> + void (*free)(struct perf_session *session);
> +};
> +
> +/**
> * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
> * @base: address of mapped area
> * @userpg: pointer to buffer's perf_event_mmap_page
> @@ -168,4 +187,40 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
> struct perf_session *session,
> perf_event__handler_t process);
>
> +static inline int auxtrace__process_event(struct perf_session *session,
> + union perf_event *event,
> + struct perf_sample *sample,
> + struct perf_tool *tool)
> +{
> + if (!session->auxtrace)
> + return 0;
> +
> + return session->auxtrace->process_event(session, event, sample, tool);
> +}
> +
> +static inline int auxtrace__flush_events(struct perf_session *session,
> + struct perf_tool *tool)
> +{
> + if (!session->auxtrace)
> + return 0;
> +
> + return session->auxtrace->flush_events(session, tool);
> +}
> +
> +static inline void auxtrace__free_events(struct perf_session *session)
> +{
> + if (!session->auxtrace)
> + return;
> +
> + return session->auxtrace->free_events(session);
> +}
> +
> +static inline void auxtrace__free(struct perf_session *session)
> +{
> + if (!session->auxtrace)
> + return;
> +
> + return session->auxtrace->free(session);
> +}
> +
> #endif
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index 18e4034..cf9d678 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -15,12 +15,13 @@
> #include "cpumap.h"
> #include "perf_regs.h"
> #include "asm/bug.h"
> +#include "auxtrace.h"
>
> -static int machines__deliver_event(struct machines *machines,
> - struct perf_evlist *evlist,
> - union perf_event *event,
> - struct perf_sample *sample,
> - struct perf_tool *tool, u64 file_offset);
> +static int perf_session__deliver_event(struct perf_session *session,
> + union perf_event *event,
> + struct perf_sample *sample,
> + struct perf_tool *tool,
> + u64 file_offset);
>
> static int perf_session__open(struct perf_session *session)
> {
> @@ -105,8 +106,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
> return ret;
> }
>
> - return machines__deliver_event(&session->machines, session->evlist, event->event,
> - &sample, session->tool, event->file_offset);
> + return perf_session__deliver_event(session, event->event, &sample,
> + session->tool, event->file_offset);
> }
>
> struct perf_session *perf_session__new(struct perf_data_file *file,
> @@ -185,6 +186,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
>
> void perf_session__delete(struct perf_session *session)
> {
> + auxtrace__free(session);
> perf_session__destroy_kernel_maps(session);
> perf_session__delete_threads(session);
> perf_session_env__delete(&session->header.env);
> @@ -1030,6 +1032,24 @@ static int machines__deliver_event(struct machines *machines,
> }
> }
>
> +static int perf_session__deliver_event(struct perf_session *session,
> + union perf_event *event,
> + struct perf_sample *sample,
> + struct perf_tool *tool,
> + u64 file_offset)
> +{
> + int ret;
> +
> + ret = auxtrace__process_event(session, event, sample, tool);
> + if (ret < 0)
> + return ret;
> + if (ret > 0)
> + return 0;
> +
> + return machines__deliver_event(&session->machines, session->evlist,
> + event, sample, tool, file_offset);
> +}
> +
> static s64 perf_session__process_user_event(struct perf_session *session,
> union perf_event *event,
> u64 file_offset)
> @@ -1190,8 +1210,8 @@ static s64 perf_session__process_event(struct perf_session *session,
> return ret;
> }
>
> - return machines__deliver_event(&session->machines, evlist, event,
> - &sample, tool, file_offset);
> + return perf_session__deliver_event(session, event, &sample, tool,
> + file_offset);
> }
>
> void perf_event_header__bswap(struct perf_event_header *hdr)
> @@ -1350,10 +1370,14 @@ more:
> done:
> /* do the final flush for ordered samples */
> err = ordered_events__flush(oe, OE_FLUSH__FINAL);
> + if (err)
> + goto out_err;
> + err = auxtrace__flush_events(session, tool);
> out_err:
> free(buf);
> perf_session__warn_about_errors(session);
> ordered_events__free(&session->ordered_events);
> + auxtrace__free_events(session);
> return err;
> }
>
> @@ -1496,10 +1520,14 @@ more:
> out:
> /* do the final flush for ordered samples */
> err = ordered_events__flush(oe, OE_FLUSH__FINAL);
> + if (err)
> + goto out_err;
> + err = auxtrace__flush_events(session, tool);
> out_err:
> ui_progress__finish();
> perf_session__warn_about_errors(session);
> ordered_events__free(&session->ordered_events);
> + auxtrace__free_events(session);
> session->one_mmap = false;
> return err;
> }
> @@ -1582,7 +1610,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
>
> size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
> {
> - size_t ret = fprintf(fp, "Aggregated stats:\n");
> + size_t ret;
> + const char *msg = "";
> +
> + if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
> + msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
> +
> + ret = fprintf(fp, "Aggregated stats:%s\n", msg);
>
> ret += events_stats__fprintf(&session->evlist->stats, fp);
> return ret;
> diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
> index d5fa7b791..8a69d3b 100644
> --- a/tools/perf/util/session.h
> +++ b/tools/perf/util/session.h
> @@ -15,10 +15,13 @@
> struct ip_callchain;
> struct thread;
>
> +struct auxtrace;
> +
> struct perf_session {
> struct perf_header header;
> struct machines machines;
> struct perf_evlist *evlist;
> + struct auxtrace *auxtrace;
> struct trace_event tevent;
> bool repipe;
> bool one_mmap;
> --
> 1.9.1
^ permalink raw reply [flat|nested] 79+ messages in thread* Re: [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data
2015-04-21 14:41 ` Arnaldo Carvalho de Melo
@ 2015-04-21 14:46 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-21 14:46 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Tue, Apr 21, 2015 at 11:41:54AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Apr 09, 2015 at 06:53:48PM +0300, Adrian Hunter escreveu:
> > Hook into session processing so that AUX area decoding can
> > synthesize events transparently to the tools.
> >
> > The advantages of transparent decoding are that tools can be used
> > directly with perf.data files containing AUX area tracing data,
> > which is easier for the user and more efficient than having a
> > separate decoding tool.
> >
> > This will work as follows:
> > 1. Tools will feed auxtrace events to the decoder using
> > perf_tool->auxtrace() (support for that still to come).
> > 2. The decoder can process side-band events as needed due
> > to the auxtrace->process_event() hook.
> > 3. The decoder can deliver synthesized events into the
> > event stream using perf_session__deliver_synth_event().
>
> So, here this clashes with work I'm doing to untie ordered_events from
> perf_session, undoes it even, trying to decipher if this is really
> needed...
Sorry, gut reaction, it only touches perf_session code, it can be left
for later to figure out if that auxtrace fits better in 'struct
perf_evlist' or even 'struct machine', as perf_session is about a
'perf.data' file, i.e. post processing.
But I think that processing intel PT events _as they are generated_ (in
fact as fast as possible, as there is buffering, etc), i.e. a la 'perf
trace' or 'perf top' will be difficult/impossible, given its volume...
But perhaps with some filtering/narrowing... anyway, will leave this for
later, applying this patch.
- Arnaldo
> - Arnaldo
>
> > Note the expectation is that decoding will work on data that is
> > time-ordered with respect to the per-cpu or per-thread contexts
> > that were recorded.
>
> > Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> > ---
> > tools/perf/util/auxtrace.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
> > tools/perf/util/session.c | 54 ++++++++++++++++++++++++++++++++++++---------
> > tools/perf/util/session.h | 3 +++
> > 3 files changed, 102 insertions(+), 10 deletions(-)
> >
> > diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
> > index 7ab4850..199fc27 100644
> > --- a/tools/perf/util/auxtrace.h
> > +++ b/tools/perf/util/auxtrace.h
> > @@ -23,6 +23,7 @@
> > #include <linux/types.h>
> >
> > #include "../perf.h"
> > +#include "session.h"
> >
> > union perf_event;
> > struct perf_session;
> > @@ -32,6 +33,24 @@ struct record_opts;
> > struct auxtrace_info_event;
> >
> > /**
> > + * struct auxtrace - session callbacks to allow AUX area data decoding.
> > + * @process_event: lets the decoder see all session events
> > + * @flush_events: process any remaining data
> > + * @free_events: free resources associated with event processing
> > + * @free: free resources associated with the session
> > + */
> > +struct auxtrace {
> > + int (*process_event)(struct perf_session *session,
> > + union perf_event *event,
> > + struct perf_sample *sample,
> > + struct perf_tool *tool);
> > + int (*flush_events)(struct perf_session *session,
> > + struct perf_tool *tool);
> > + void (*free_events)(struct perf_session *session);
> > + void (*free)(struct perf_session *session);
> > +};
> > +
> > +/**
> > * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
> > * @base: address of mapped area
> > * @userpg: pointer to buffer's perf_event_mmap_page
> > @@ -168,4 +187,40 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
> > struct perf_session *session,
> > perf_event__handler_t process);
> >
> > +static inline int auxtrace__process_event(struct perf_session *session,
> > + union perf_event *event,
> > + struct perf_sample *sample,
> > + struct perf_tool *tool)
> > +{
> > + if (!session->auxtrace)
> > + return 0;
> > +
> > + return session->auxtrace->process_event(session, event, sample, tool);
> > +}
> > +
> > +static inline int auxtrace__flush_events(struct perf_session *session,
> > + struct perf_tool *tool)
> > +{
> > + if (!session->auxtrace)
> > + return 0;
> > +
> > + return session->auxtrace->flush_events(session, tool);
> > +}
> > +
> > +static inline void auxtrace__free_events(struct perf_session *session)
> > +{
> > + if (!session->auxtrace)
> > + return;
> > +
> > + return session->auxtrace->free_events(session);
> > +}
> > +
> > +static inline void auxtrace__free(struct perf_session *session)
> > +{
> > + if (!session->auxtrace)
> > + return;
> > +
> > + return session->auxtrace->free(session);
> > +}
> > +
> > #endif
> > diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> > index 18e4034..cf9d678 100644
> > --- a/tools/perf/util/session.c
> > +++ b/tools/perf/util/session.c
> > @@ -15,12 +15,13 @@
> > #include "cpumap.h"
> > #include "perf_regs.h"
> > #include "asm/bug.h"
> > +#include "auxtrace.h"
> >
> > -static int machines__deliver_event(struct machines *machines,
> > - struct perf_evlist *evlist,
> > - union perf_event *event,
> > - struct perf_sample *sample,
> > - struct perf_tool *tool, u64 file_offset);
> > +static int perf_session__deliver_event(struct perf_session *session,
> > + union perf_event *event,
> > + struct perf_sample *sample,
> > + struct perf_tool *tool,
> > + u64 file_offset);
> >
> > static int perf_session__open(struct perf_session *session)
> > {
> > @@ -105,8 +106,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
> > return ret;
> > }
> >
> > - return machines__deliver_event(&session->machines, session->evlist, event->event,
> > - &sample, session->tool, event->file_offset);
> > + return perf_session__deliver_event(session, event->event, &sample,
> > + session->tool, event->file_offset);
> > }
> >
> > struct perf_session *perf_session__new(struct perf_data_file *file,
> > @@ -185,6 +186,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
> >
> > void perf_session__delete(struct perf_session *session)
> > {
> > + auxtrace__free(session);
> > perf_session__destroy_kernel_maps(session);
> > perf_session__delete_threads(session);
> > perf_session_env__delete(&session->header.env);
> > @@ -1030,6 +1032,24 @@ static int machines__deliver_event(struct machines *machines,
> > }
> > }
> >
> > +static int perf_session__deliver_event(struct perf_session *session,
> > + union perf_event *event,
> > + struct perf_sample *sample,
> > + struct perf_tool *tool,
> > + u64 file_offset)
> > +{
> > + int ret;
> > +
> > + ret = auxtrace__process_event(session, event, sample, tool);
> > + if (ret < 0)
> > + return ret;
> > + if (ret > 0)
> > + return 0;
> > +
> > + return machines__deliver_event(&session->machines, session->evlist,
> > + event, sample, tool, file_offset);
> > +}
> > +
> > static s64 perf_session__process_user_event(struct perf_session *session,
> > union perf_event *event,
> > u64 file_offset)
> > @@ -1190,8 +1210,8 @@ static s64 perf_session__process_event(struct perf_session *session,
> > return ret;
> > }
> >
> > - return machines__deliver_event(&session->machines, evlist, event,
> > - &sample, tool, file_offset);
> > + return perf_session__deliver_event(session, event, &sample, tool,
> > + file_offset);
> > }
> >
> > void perf_event_header__bswap(struct perf_event_header *hdr)
> > @@ -1350,10 +1370,14 @@ more:
> > done:
> > /* do the final flush for ordered samples */
> > err = ordered_events__flush(oe, OE_FLUSH__FINAL);
> > + if (err)
> > + goto out_err;
> > + err = auxtrace__flush_events(session, tool);
> > out_err:
> > free(buf);
> > perf_session__warn_about_errors(session);
> > ordered_events__free(&session->ordered_events);
> > + auxtrace__free_events(session);
> > return err;
> > }
> >
> > @@ -1496,10 +1520,14 @@ more:
> > out:
> > /* do the final flush for ordered samples */
> > err = ordered_events__flush(oe, OE_FLUSH__FINAL);
> > + if (err)
> > + goto out_err;
> > + err = auxtrace__flush_events(session, tool);
> > out_err:
> > ui_progress__finish();
> > perf_session__warn_about_errors(session);
> > ordered_events__free(&session->ordered_events);
> > + auxtrace__free_events(session);
> > session->one_mmap = false;
> > return err;
> > }
> > @@ -1582,7 +1610,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
> >
> > size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
> > {
> > - size_t ret = fprintf(fp, "Aggregated stats:\n");
> > + size_t ret;
> > + const char *msg = "";
> > +
> > + if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
> > + msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
> > +
> > + ret = fprintf(fp, "Aggregated stats:%s\n", msg);
> >
> > ret += events_stats__fprintf(&session->evlist->stats, fp);
> > return ret;
> > diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
> > index d5fa7b791..8a69d3b 100644
> > --- a/tools/perf/util/session.h
> > +++ b/tools/perf/util/session.h
> > @@ -15,10 +15,13 @@
> > struct ip_callchain;
> > struct thread;
> >
> > +struct auxtrace;
> > +
> > struct perf_session {
> > struct perf_header header;
> > struct machines machines;
> > struct perf_evlist *evlist;
> > + struct auxtrace *auxtrace;
> > struct trace_event tevent;
> > bool repipe;
> > bool one_mmap;
> > --
> > 1.9.1
^ permalink raw reply [flat|nested] 79+ messages in thread
* [tip:perf/core] perf session: Add hooks to allow transparent decoding of AUX area tracing data
2015-04-09 15:53 ` [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data Adrian Hunter
2015-04-21 14:41 ` Arnaldo Carvalho de Melo
@ 2015-05-06 3:00 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:00 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, dsahern, peterz, namhyung, mingo, tglx, jolsa,
linux-kernel, adrian.hunter, fweisbec, eranian, hpa
Commit-ID: c446870d80f37281a927b5f6984bd47397a7cb03
Gitweb: http://git.kernel.org/tip/c446870d80f37281a927b5f6984bd47397a7cb03
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:48 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:53 -0300
perf session: Add hooks to allow transparent decoding of AUX area tracing data
Hook into session processing so that AUX area decoding can synthesize
events transparently to the tools.
The advantages of transparent decoding are that tools can be used
directly with perf.data files containing AUX area tracing data, which is
easier for the user and more efficient than having a separate decoding
tool.
This will work as follows:
1. Tools will feed auxtrace events to the decoder using
perf_tool->auxtrace() (support for that still to come).
2. The decoder can process side-band events as needed due
to the auxtrace->process_event() hook.
3. The decoder can deliver synthesized events into the
event stream using perf_session__deliver_synth_event().
Note the expectation is that decoding will work on data that is
time-ordered with respect to the per-cpu or per-thread contexts that
were recorded.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-9-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/session.c | 54 ++++++++++++++++++++++++++++++++++++---------
tools/perf/util/session.h | 3 +++
3 files changed, 102 insertions(+), 10 deletions(-)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 7ab4850..199fc27 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include "../perf.h"
+#include "session.h"
union perf_event;
struct perf_session;
@@ -32,6 +33,24 @@ struct record_opts;
struct auxtrace_info_event;
/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+ int (*process_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool);
+ int (*flush_events)(struct perf_session *session,
+ struct perf_tool *tool);
+ void (*free_events)(struct perf_session *session);
+ void (*free)(struct perf_session *session);
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -168,4 +187,40 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_session *session,
perf_event__handler_t process);
+static inline int auxtrace__process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free(session);
+}
+
#endif
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4008dab..7271c6b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,13 @@
#include "cpumap.h"
#include "perf_regs.h"
#include "asm/bug.h"
+#include "auxtrace.h"
-static int machines__deliver_event(struct machines *machines,
- struct perf_evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset);
static int perf_session__open(struct perf_session *session)
{
@@ -105,8 +106,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
return ret;
}
- return machines__deliver_event(&session->machines, session->evlist, event->event,
- &sample, session->tool, event->file_offset);
+ return perf_session__deliver_event(session, event->event, &sample,
+ session->tool, event->file_offset);
}
struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -185,6 +186,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
void perf_session__delete(struct perf_session *session)
{
+ auxtrace__free(session);
perf_session__destroy_kernel_maps(session);
perf_session__delete_threads(session);
perf_session_env__delete(&session->header.env);
@@ -1030,6 +1032,24 @@ static int machines__deliver_event(struct machines *machines,
}
}
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset)
+{
+ int ret;
+
+ ret = auxtrace__process_event(session, event, sample, tool);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ return 0;
+
+ return machines__deliver_event(&session->machines, session->evlist,
+ event, sample, tool, file_offset);
+}
+
static s64 perf_session__process_user_event(struct perf_session *session,
union perf_event *event,
u64 file_offset)
@@ -1190,8 +1210,8 @@ static s64 perf_session__process_event(struct perf_session *session,
return ret;
}
- return machines__deliver_event(&session->machines, evlist, event,
- &sample, tool, file_offset);
+ return perf_session__deliver_event(session, event, &sample, tool,
+ file_offset);
}
void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1350,10 +1370,14 @@ more:
done:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
free(buf);
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
return err;
}
@@ -1496,10 +1520,14 @@ more:
out:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
ui_progress__finish();
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
session->one_mmap = false;
return err;
}
@@ -1582,7 +1610,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
{
- size_t ret = fprintf(fp, "Aggregated stats:\n");
+ size_t ret;
+ const char *msg = "";
+
+ if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+ ret = fprintf(fp, "Aggregated stats:%s\n", msg);
ret += events_stats__fprintf(&session->evlist->stats, fp);
return ret;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b791..8a69d3b 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,13 @@
struct ip_callchain;
struct thread;
+struct auxtrace;
+
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
+ struct auxtrace *auxtrace;
struct trace_event tevent;
bool repipe;
bool one_mmap;
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 09/44] perf session: Add instruction tracing options
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (7 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 08/44] perf session: Add hooks to allow transparent decoding of AUX area tracing data Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-21 14:50 ` Arnaldo Carvalho de Melo
2015-05-06 3:00 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 10/44] perf auxtrace: Add helpers for AUX area tracing errors Adrian Hunter
` (34 subsequent siblings)
43 siblings, 2 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
It is assumed that AUX area decoding will
synthesize events for consumption by other tools.
At this time, the main use of AUX area tracing will be
to capture instruction trace (aka processor trace) data.
The nature of instruction tracing suggests the
initial inclusion of options for "instructions"
and "branches" events, but more could be added
as needed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 131 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 43 +++++++++++++++
tools/perf/util/session.h | 2 +
3 files changed, 176 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 2cafea2..1bec3e6 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -37,6 +37,7 @@
#include "event.h"
#include "debug.h"
+#include "parse-options.h"
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
@@ -200,6 +201,136 @@ out_free:
return err;
}
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD 100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+ synth_opts->instructions = true;
+ synth_opts->branches = true;
+ synth_opts->errors = true;
+ synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset)
+{
+ struct itrace_synth_opts *synth_opts = opt->value;
+ const char *p;
+ char *endptr;
+
+ synth_opts->set = true;
+
+ if (unset) {
+ synth_opts->dont_decode = true;
+ return 0;
+ }
+
+ if (!str) {
+ itrace_synth_opts__set_default(synth_opts);
+ return 0;
+ }
+
+ for (p = str; *p;) {
+ switch (*p++) {
+ case 'i':
+ synth_opts->instructions = true;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ synth_opts->period = strtoull(p, &endptr, 10);
+ p = endptr;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ switch (*p++) {
+ case 'i':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_INSTRUCTIONS;
+ break;
+ case 't':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_TICKS;
+ break;
+ case 'm':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'u':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'n':
+ if (*p++ != 's')
+ goto out_err;
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_NANOSECS;
+ break;
+ case '\0':
+ goto out;
+ default:
+ goto out_err;
+ }
+ }
+ break;
+ case 'b':
+ synth_opts->branches = true;
+ break;
+ case 'e':
+ synth_opts->errors = true;
+ break;
+ case 'd':
+ synth_opts->log = true;
+ break;
+ case 'c':
+ synth_opts->branches = true;
+ synth_opts->calls = true;
+ break;
+ case 'r':
+ synth_opts->branches = true;
+ synth_opts->returns = true;
+ break;
+ case 'g':
+ synth_opts->instructions = true;
+ synth_opts->callchain = true;
+ synth_opts->callchain_sz =
+ PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ unsigned int val;
+
+ val = strtoul(p, &endptr, 10);
+ p = endptr;
+ if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+ goto out_err;
+ synth_opts->callchain_sz = val;
+ }
+ break;
+ case ' ':
+ case ',':
+ break;
+ default:
+ goto out_err;
+ }
+ }
+out:
+ if (synth_opts->instructions) {
+ if (!synth_opts->period_type)
+ synth_opts->period_type =
+ PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ if (!synth_opts->period)
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ }
+
+ return 0;
+
+out_err:
+ pr_err("Bad Instruction Tracing options '%s'\n", str);
+ return -EINVAL;
+}
+
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn)
{
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 199fc27..6355315 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,9 +29,49 @@ union perf_event;
struct perf_session;
struct perf_evlist;
struct perf_tool;
+struct option;
struct record_opts;
struct auxtrace_info_event;
+enum itrace_period_type {
+ PERF_ITRACE_PERIOD_INSTRUCTIONS,
+ PERF_ITRACE_PERIOD_TICKS,
+ PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ * because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+ bool set;
+ bool inject;
+ bool instructions;
+ bool branches;
+ bool errors;
+ bool dont_decode;
+ bool log;
+ bool calls;
+ bool returns;
+ bool callchain;
+ unsigned int callchain_sz;
+ unsigned long long period;
+ enum itrace_period_type period_type;
+};
+
/**
* struct auxtrace - session callbacks to allow AUX area data decoding.
* @process_event: lets the decoder see all session events
@@ -186,6 +226,9 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
static inline int auxtrace__process_event(struct perf_session *session,
union perf_event *event,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 8a69d3b..9ed5135 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -16,12 +16,14 @@ struct ip_callchain;
struct thread;
struct auxtrace;
+struct itrace_synth_opts;
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
struct auxtrace *auxtrace;
+ struct itrace_synth_opts *itrace_synth_opts;
struct trace_event tevent;
bool repipe;
bool one_mmap;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 09/44] perf session: Add instruction tracing options
2015-04-09 15:53 ` [PATCH 09/44] perf session: Add instruction tracing options Adrian Hunter
@ 2015-04-21 14:50 ` Arnaldo Carvalho de Melo
2015-04-22 6:23 ` Adrian Hunter
2015-05-06 3:00 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 1 reply; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-21 14:50 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:49PM +0300, Adrian Hunter escreveu:
> It is assumed that AUX area decoding will synthesize events for
> consumption by other tools. At this time, the main use of AUX area
> tracing will be to capture instruction trace (aka processor trace)
> data. The nature of instruction tracing suggests the initial
> inclusion of options for "instructions" and "branches" events, but
> more could be added as needed.
> +++ b/tools/perf/util/auxtrace.c
> @@ -37,6 +37,7 @@
>
> #include "event.h"
> #include "debug.h"
> +#include "parse-options.h"
>
> int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
> struct auxtrace_mmap_params *mp,
> @@ -200,6 +201,136 @@ out_free:
> return err;
> }
>
> +#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
> +#define PERF_ITRACE_DEFAULT_PERIOD 100000
> +#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
> +#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
> +
> +void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
> +{
> + synth_opts->instructions = true;
> + synth_opts->branches = true;
> + synth_opts->errors = true;
> + synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
> + synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
> + synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
> +}
> +
> +int itrace_parse_synth_opts(const struct option *opt, const char *str,
> + int unset)
> +{
> + struct itrace_synth_opts *synth_opts = opt->value;
> + const char *p;
> + char *endptr;
> +
> + synth_opts->set = true;
> +
> + if (unset) {
> + synth_opts->dont_decode = true;
> + return 0;
> + }
> +
> + if (!str) {
> + itrace_synth_opts__set_default(synth_opts);
> + return 0;
> + }
> +
> + for (p = str; *p;) {
> + switch (*p++) {
> + case 'i':
> + synth_opts->instructions = true;
Is this documented anywhere? I.e. examples for setting up this synth
ops?
> + while (*p == ' ' || *p == ',')
> + p += 1;
> + if (isdigit(*p)) {
> + synth_opts->period = strtoull(p, &endptr, 10);
> + p = endptr;
> + while (*p == ' ' || *p == ',')
> + p += 1;
> + switch (*p++) {
> + case 'i':
> + synth_opts->period_type =
> + PERF_ITRACE_PERIOD_INSTRUCTIONS;
> + break;
> + case 't':
> + synth_opts->period_type =
> + PERF_ITRACE_PERIOD_TICKS;
> + break;
> + case 'm':
> + synth_opts->period *= 1000;
> + /* Fall through */
> + case 'u':
> + synth_opts->period *= 1000;
> + /* Fall through */
> + case 'n':
> + if (*p++ != 's')
> + goto out_err;
> + synth_opts->period_type =
> + PERF_ITRACE_PERIOD_NANOSECS;
> + break;
> + case '\0':
> + goto out;
> + default:
> + goto out_err;
> + }
> + }
> + break;
> + case 'b':
> + synth_opts->branches = true;
> + break;
> + case 'e':
> + synth_opts->errors = true;
> + break;
> + case 'd':
> + synth_opts->log = true;
> + break;
> + case 'c':
> + synth_opts->branches = true;
> + synth_opts->calls = true;
> + break;
> + case 'r':
> + synth_opts->branches = true;
> + synth_opts->returns = true;
> + break;
> + case 'g':
> + synth_opts->instructions = true;
> + synth_opts->callchain = true;
> + synth_opts->callchain_sz =
> + PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
> + while (*p == ' ' || *p == ',')
> + p += 1;
> + if (isdigit(*p)) {
> + unsigned int val;
> +
> + val = strtoul(p, &endptr, 10);
> + p = endptr;
> + if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
> + goto out_err;
> + synth_opts->callchain_sz = val;
> + }
> + break;
> + case ' ':
> + case ',':
> + break;
> + default:
> + goto out_err;
> + }
> + }
> +out:
> + if (synth_opts->instructions) {
> + if (!synth_opts->period_type)
> + synth_opts->period_type =
> + PERF_ITRACE_DEFAULT_PERIOD_TYPE;
> + if (!synth_opts->period)
> + synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
> + }
> +
> + return 0;
> +
> +out_err:
> + pr_err("Bad Instruction Tracing options '%s'\n", str);
> + return -EINVAL;
> +}
> +
> int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
> struct perf_tool *tool, process_auxtrace_t fn)
> {
> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
> index 199fc27..6355315 100644
> --- a/tools/perf/util/auxtrace.h
> +++ b/tools/perf/util/auxtrace.h
> @@ -29,9 +29,49 @@ union perf_event;
> struct perf_session;
> struct perf_evlist;
> struct perf_tool;
> +struct option;
> struct record_opts;
> struct auxtrace_info_event;
>
> +enum itrace_period_type {
> + PERF_ITRACE_PERIOD_INSTRUCTIONS,
> + PERF_ITRACE_PERIOD_TICKS,
> + PERF_ITRACE_PERIOD_NANOSECS,
> +};
> +
> +/**
> + * struct itrace_synth_opts - AUX area tracing synthesis options.
> + * @set: indicates whether or not options have been set
> + * @inject: indicates the event (not just the sample) must be fully synthesized
> + * because 'perf inject' will write it out
> + * @instructions: whether to synthesize 'instructions' events
> + * @branches: whether to synthesize 'branches' events
> + * @errors: whether to synthesize decoder error events
> + * @dont_decode: whether to skip decoding entirely
> + * @log: write a decoding log
> + * @calls: limit branch samples to calls (can be combined with @returns)
> + * @returns: limit branch samples to returns (can be combined with @calls)
> + * @callchain: add callchain to 'instructions' events
> + * @callchain_sz: maximum callchain size
> + * @period: 'instructions' events period
> + * @period_type: 'instructions' events period type
> + */
> +struct itrace_synth_opts {
> + bool set;
> + bool inject;
> + bool instructions;
> + bool branches;
> + bool errors;
> + bool dont_decode;
> + bool log;
> + bool calls;
> + bool returns;
> + bool callchain;
> + unsigned int callchain_sz;
> + unsigned long long period;
> + enum itrace_period_type period_type;
> +};
> +
> /**
> * struct auxtrace - session callbacks to allow AUX area data decoding.
> * @process_event: lets the decoder see all session events
> @@ -186,6 +226,9 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
> struct perf_tool *tool,
> struct perf_session *session,
> perf_event__handler_t process);
> +int itrace_parse_synth_opts(const struct option *opt, const char *str,
> + int unset);
> +void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
>
> static inline int auxtrace__process_event(struct perf_session *session,
> union perf_event *event,
> diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
> index 8a69d3b..9ed5135 100644
> --- a/tools/perf/util/session.h
> +++ b/tools/perf/util/session.h
> @@ -16,12 +16,14 @@ struct ip_callchain;
> struct thread;
>
> struct auxtrace;
> +struct itrace_synth_opts;
>
> struct perf_session {
> struct perf_header header;
> struct machines machines;
> struct perf_evlist *evlist;
> struct auxtrace *auxtrace;
> + struct itrace_synth_opts *itrace_synth_opts;
> struct trace_event tevent;
> bool repipe;
> bool one_mmap;
> --
> 1.9.1
^ permalink raw reply [flat|nested] 79+ messages in thread* Re: [PATCH 09/44] perf session: Add instruction tracing options
2015-04-21 14:50 ` Arnaldo Carvalho de Melo
@ 2015-04-22 6:23 ` Adrian Hunter
2015-04-23 14:08 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-22 6:23 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
On 21/04/15 17:50, Arnaldo Carvalho de Melo wrote:
> Em Thu, Apr 09, 2015 at 06:53:49PM +0300, Adrian Hunter escreveu:
>
>> It is assumed that AUX area decoding will synthesize events for
>> consumption by other tools. At this time, the main use of AUX area
>> tracing will be to capture instruction trace (aka processor trace)
>> data. The nature of instruction tracing suggests the initial
>> inclusion of options for "instructions" and "branches" events, but
>> more could be added as needed.
>
>> +++ b/tools/perf/util/auxtrace.c
>> @@ -37,6 +37,7 @@
>>
>> #include "event.h"
>> #include "debug.h"
>> +#include "parse-options.h"
>>
>> int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
>> struct auxtrace_mmap_params *mp,
>> @@ -200,6 +201,136 @@ out_free:
>> return err;
>> }
>>
>> +#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
>> +#define PERF_ITRACE_DEFAULT_PERIOD 100000
>> +#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
>> +#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
>> +
>> +void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
>> +{
>> + synth_opts->instructions = true;
>> + synth_opts->branches = true;
>> + synth_opts->errors = true;
>> + synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
>> + synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
>> + synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
>> +}
>> +
>> +int itrace_parse_synth_opts(const struct option *opt, const char *str,
>> + int unset)
>> +{
>> + struct itrace_synth_opts *synth_opts = opt->value;
>> + const char *p;
>> + char *endptr;
>> +
>> + synth_opts->set = true;
>> +
>> + if (unset) {
>> + synth_opts->dont_decode = true;
>> + return 0;
>> + }
>> +
>> + if (!str) {
>> + itrace_synth_opts__set_default(synth_opts);
>> + return 0;
>> + }
>> +
>> + for (p = str; *p;) {
>> + switch (*p++) {
>> + case 'i':
>> + synth_opts->instructions = true;
>
> Is this documented anywhere? I.e. examples for setting up this synth
> ops?
They are documented for each tool that uses them:
Documentation/perf-script.txt
Documentation/perf-record.txt
and also in:
Documentation/intel-pt.txt
^ permalink raw reply [flat|nested] 79+ messages in thread* Re: [PATCH 09/44] perf session: Add instruction tracing options
2015-04-22 6:23 ` Adrian Hunter
@ 2015-04-23 14:08 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-23 14:08 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Wed, Apr 22, 2015 at 09:23:09AM +0300, Adrian Hunter escreveu:
> On 21/04/15 17:50, Arnaldo Carvalho de Melo wrote:
> > Em Thu, Apr 09, 2015 at 06:53:49PM +0300, Adrian Hunter escreveu:
> >
> >> It is assumed that AUX area decoding will synthesize events for
> >> consumption by other tools. At this time, the main use of AUX area
> >> tracing will be to capture instruction trace (aka processor trace)
> >> data. The nature of instruction tracing suggests the initial
> >> inclusion of options for "instructions" and "branches" events, but
> >> more could be added as needed.
> >
> >> +++ b/tools/perf/util/auxtrace.c
> >> @@ -37,6 +37,7 @@
> >>
> >> #include "event.h"
> >> #include "debug.h"
> >> +#include "parse-options.h"
> >>
> >> int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
> >> struct auxtrace_mmap_params *mp,
> >> @@ -200,6 +201,136 @@ out_free:
> >> return err;
> >> }
> >>
> >> +#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
> >> +#define PERF_ITRACE_DEFAULT_PERIOD 100000
> >> +#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
> >> +#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
> >> +
> >> +void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
> >> +{
> >> + synth_opts->instructions = true;
> >> + synth_opts->branches = true;
> >> + synth_opts->errors = true;
> >> + synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
> >> + synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
> >> + synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
> >> +}
> >> +
> >> +int itrace_parse_synth_opts(const struct option *opt, const char *str,
> >> + int unset)
> >> +{
> >> + struct itrace_synth_opts *synth_opts = opt->value;
> >> + const char *p;
> >> + char *endptr;
> >> +
> >> + synth_opts->set = true;
> >> +
> >> + if (unset) {
> >> + synth_opts->dont_decode = true;
> >> + return 0;
> >> + }
> >> +
> >> + if (!str) {
> >> + itrace_synth_opts__set_default(synth_opts);
> >> + return 0;
> >> + }
> >> +
> >> + for (p = str; *p;) {
> >> + switch (*p++) {
> >> + case 'i':
> >> + synth_opts->instructions = true;
> >
> > Is this documented anywhere? I.e. examples for setting up this synth
> > ops?
>
> They are documented for each tool that uses them:
> Documentation/perf-script.txt
> Documentation/perf-record.txt
> and also in:
> Documentation/intel-pt.txt
That comes later in the patchkit, right? I am ammending this patch to
put a reference to these files, which ammeliorates the current
situation, but people doing bisects will scratch their heads...
- Arnaldo
^ permalink raw reply [flat|nested] 79+ messages in thread
* [tip:perf/core] perf session: Add instruction tracing options
2015-04-09 15:53 ` [PATCH 09/44] perf session: Add instruction tracing options Adrian Hunter
2015-04-21 14:50 ` Arnaldo Carvalho de Melo
@ 2015-05-06 3:00 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:00 UTC (permalink / raw)
To: linux-tip-commits
Cc: jolsa, dsahern, adrian.hunter, eranian, fweisbec, hpa, acme,
peterz, namhyung, linux-kernel, tglx, mingo
Commit-ID: f6986c95af84ff2a76847910b4322f542b793bbf
Gitweb: http://git.kernel.org/tip/f6986c95af84ff2a76847910b4322f542b793bbf
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:49 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:53 -0300
perf session: Add instruction tracing options
It is assumed that AUX area decoding will synthesize events for
consumption by other tools.
At this time, the main use of AUX area tracing will be to capture
instruction trace (aka processor trace) data.
The nature of instruction tracing suggests the initial inclusion of
options for "instructions" and "branches" events, but more could be
added as needed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-10-git-send-email-adrian.hunter@intel.com
[ Added ref to tools/perf/Documentation/perf-script.txt describing what is parsed ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 136 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 43 ++++++++++++++
tools/perf/util/session.h | 2 +
3 files changed, 181 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 2cafea2..db40d6c 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -37,6 +37,7 @@
#include "event.h"
#include "debug.h"
+#include "parse-options.h"
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
@@ -200,6 +201,141 @@ out_free:
return err;
}
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD 100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+ synth_opts->instructions = true;
+ synth_opts->branches = true;
+ synth_opts->errors = true;
+ synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset)
+{
+ struct itrace_synth_opts *synth_opts = opt->value;
+ const char *p;
+ char *endptr;
+
+ synth_opts->set = true;
+
+ if (unset) {
+ synth_opts->dont_decode = true;
+ return 0;
+ }
+
+ if (!str) {
+ itrace_synth_opts__set_default(synth_opts);
+ return 0;
+ }
+
+ for (p = str; *p;) {
+ switch (*p++) {
+ case 'i':
+ synth_opts->instructions = true;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ synth_opts->period = strtoull(p, &endptr, 10);
+ p = endptr;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ switch (*p++) {
+ case 'i':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_INSTRUCTIONS;
+ break;
+ case 't':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_TICKS;
+ break;
+ case 'm':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'u':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'n':
+ if (*p++ != 's')
+ goto out_err;
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_NANOSECS;
+ break;
+ case '\0':
+ goto out;
+ default:
+ goto out_err;
+ }
+ }
+ break;
+ case 'b':
+ synth_opts->branches = true;
+ break;
+ case 'e':
+ synth_opts->errors = true;
+ break;
+ case 'd':
+ synth_opts->log = true;
+ break;
+ case 'c':
+ synth_opts->branches = true;
+ synth_opts->calls = true;
+ break;
+ case 'r':
+ synth_opts->branches = true;
+ synth_opts->returns = true;
+ break;
+ case 'g':
+ synth_opts->instructions = true;
+ synth_opts->callchain = true;
+ synth_opts->callchain_sz =
+ PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ unsigned int val;
+
+ val = strtoul(p, &endptr, 10);
+ p = endptr;
+ if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+ goto out_err;
+ synth_opts->callchain_sz = val;
+ }
+ break;
+ case ' ':
+ case ',':
+ break;
+ default:
+ goto out_err;
+ }
+ }
+out:
+ if (synth_opts->instructions) {
+ if (!synth_opts->period_type)
+ synth_opts->period_type =
+ PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ if (!synth_opts->period)
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ }
+
+ return 0;
+
+out_err:
+ pr_err("Bad Instruction Tracing options '%s'\n", str);
+ return -EINVAL;
+}
+
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn)
{
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 199fc27..6355315 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,9 +29,49 @@ union perf_event;
struct perf_session;
struct perf_evlist;
struct perf_tool;
+struct option;
struct record_opts;
struct auxtrace_info_event;
+enum itrace_period_type {
+ PERF_ITRACE_PERIOD_INSTRUCTIONS,
+ PERF_ITRACE_PERIOD_TICKS,
+ PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ * because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+ bool set;
+ bool inject;
+ bool instructions;
+ bool branches;
+ bool errors;
+ bool dont_decode;
+ bool log;
+ bool calls;
+ bool returns;
+ bool callchain;
+ unsigned int callchain_sz;
+ unsigned long long period;
+ enum itrace_period_type period_type;
+};
+
/**
* struct auxtrace - session callbacks to allow AUX area data decoding.
* @process_event: lets the decoder see all session events
@@ -186,6 +226,9 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
static inline int auxtrace__process_event(struct perf_session *session,
union perf_event *event,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 8a69d3b..9ed5135 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -16,12 +16,14 @@ struct ip_callchain;
struct thread;
struct auxtrace;
+struct itrace_synth_opts;
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
struct auxtrace *auxtrace;
+ struct itrace_synth_opts *itrace_synth_opts;
struct trace_event tevent;
bool repipe;
bool one_mmap;
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 10/44] perf auxtrace: Add helpers for AUX area tracing errors
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (8 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 09/44] perf session: Add instruction tracing options Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:01 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 11/44] perf auxtrace: Add helpers for queuing AUX area tracing data Adrian Hunter
` (33 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add functions to synthesize, count and print
AUX area tracing error events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 14 ++++++++
tools/perf/util/event.h | 6 ++++
tools/perf/util/session.c | 3 ++
4 files changed, 104 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 1bec3e6..9073fe2 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -24,6 +24,7 @@
#include <linux/log2.h>
#include <stdlib.h>
+#include <stdio.h>
#include <string.h>
#include <errno.h>
@@ -36,6 +37,7 @@
#include "auxtrace.h"
#include "event.h"
+#include "session.h"
#include "debug.h"
#include "parse-options.h"
@@ -172,6 +174,28 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg)
+{
+ size_t size;
+
+ memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+ auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+ auxtrace_error->type = type;
+ auxtrace_error->code = code;
+ auxtrace_error->cpu = cpu;
+ auxtrace_error->pid = pid;
+ auxtrace_error->tid = tid;
+ auxtrace_error->ip = ip;
+ strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+ size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+ strlen(auxtrace_error->msg) + 1;
+ auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
@@ -331,6 +355,63 @@ out_err:
return -EINVAL;
}
+static const char * const auxtrace_error_type_name[] = {
+ [PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+ const char *error_type_name = NULL;
+
+ if (type < PERF_AUXTRACE_ERROR_MAX)
+ error_type_name = auxtrace_error_type_name[type];
+ if (!error_type_name)
+ error_type_name = "unknown AUX";
+ return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+ int ret;
+
+ ret = fprintf(fp, " %s error type %u",
+ auxtrace_error_name(e->type), e->type);
+ ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+ e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+ return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+
+ if (e->type < PERF_AUXTRACE_ERROR_MAX)
+ session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+ int i;
+
+ for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+ if (!stats->nr_auxtrace_errors[i])
+ continue;
+ ui__warning("%u %s errors\n",
+ stats->nr_auxtrace_errors[i],
+ auxtrace_error_name(i));
+ }
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ perf_event__fprintf_auxtrace_error(event, stdout);
+ return 0;
+}
+
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn)
{
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 6355315..bcfb928 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include "../perf.h"
+#include "event.h"
#include "session.h"
union perf_event;
@@ -32,6 +33,7 @@ struct perf_tool;
struct option;
struct record_opts;
struct auxtrace_info_event;
+struct events_stats;
enum itrace_period_type {
PERF_ITRACE_PERIOD_INSTRUCTIONS,
@@ -222,14 +224,26 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
void auxtrace_record__free(struct auxtrace_record *itr);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg);
+
int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
int itrace_parse_synth_opts(const struct option *opt, const char *str,
int unset);
void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
static inline int auxtrace__process_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 657dcfa..8ef3725 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -221,6 +221,11 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_MAX
};
+enum auxtrace_error_type {
+ PERF_AUXTRACE_ERROR_ITRACE = 1,
+ PERF_AUXTRACE_ERROR_MAX
+};
+
/*
* The kernel collects the number of events it couldn't send in a stretch and
* when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -245,6 +250,7 @@ struct events_stats {
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
+ u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
};
struct attr_event {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cf9d678..b08bf15 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1093,6 +1093,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
lseek(fd, file_offset + event->header.size, SEEK_SET);
return tool->auxtrace(tool, event, session);
case PERF_RECORD_AUXTRACE_ERROR:
+ perf_session__auxtrace_error_inc(session, event);
return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
@@ -1282,6 +1283,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
if (oe->nr_unordered_events != 0)
ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+ events_stats__auxtrace_error_warn(stats);
}
volatile int session_done;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add helpers for AUX area tracing errors
2015-04-09 15:53 ` [PATCH 10/44] perf auxtrace: Add helpers for AUX area tracing errors Adrian Hunter
@ 2015-05-06 3:01 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:01 UTC (permalink / raw)
To: linux-tip-commits
Cc: mingo, adrian.hunter, namhyung, eranian, tglx, peterz, jolsa,
hpa, fweisbec, acme, dsahern, linux-kernel
Commit-ID: 85ed47299e979b861e314c2e177a6de5d9163a85
Gitweb: http://git.kernel.org/tip/85ed47299e979b861e314c2e177a6de5d9163a85
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:50 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:53 -0300
perf auxtrace: Add helpers for AUX area tracing errors
Add functions to synthesize, count and print AUX area tracing error
events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-11-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 14 ++++++++
tools/perf/util/event.h | 6 ++++
tools/perf/util/session.c | 3 ++
4 files changed, 104 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db40d6c..905188b 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -24,6 +24,7 @@
#include <linux/log2.h>
#include <stdlib.h>
+#include <stdio.h>
#include <string.h>
#include <errno.h>
@@ -36,6 +37,7 @@
#include "auxtrace.h"
#include "event.h"
+#include "session.h"
#include "debug.h"
#include "parse-options.h"
@@ -172,6 +174,28 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg)
+{
+ size_t size;
+
+ memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+ auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+ auxtrace_error->type = type;
+ auxtrace_error->code = code;
+ auxtrace_error->cpu = cpu;
+ auxtrace_error->pid = pid;
+ auxtrace_error->tid = tid;
+ auxtrace_error->ip = ip;
+ strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+ size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+ strlen(auxtrace_error->msg) + 1;
+ auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
@@ -336,6 +360,63 @@ out_err:
return -EINVAL;
}
+static const char * const auxtrace_error_type_name[] = {
+ [PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+ const char *error_type_name = NULL;
+
+ if (type < PERF_AUXTRACE_ERROR_MAX)
+ error_type_name = auxtrace_error_type_name[type];
+ if (!error_type_name)
+ error_type_name = "unknown AUX";
+ return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+ int ret;
+
+ ret = fprintf(fp, " %s error type %u",
+ auxtrace_error_name(e->type), e->type);
+ ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+ e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+ return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+
+ if (e->type < PERF_AUXTRACE_ERROR_MAX)
+ session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+ int i;
+
+ for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+ if (!stats->nr_auxtrace_errors[i])
+ continue;
+ ui__warning("%u %s errors\n",
+ stats->nr_auxtrace_errors[i],
+ auxtrace_error_name(i));
+ }
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ perf_event__fprintf_auxtrace_error(event, stdout);
+ return 0;
+}
+
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn)
{
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 6355315..bcfb928 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include "../perf.h"
+#include "event.h"
#include "session.h"
union perf_event;
@@ -32,6 +33,7 @@ struct perf_tool;
struct option;
struct record_opts;
struct auxtrace_info_event;
+struct events_stats;
enum itrace_period_type {
PERF_ITRACE_PERIOD_INSTRUCTIONS,
@@ -222,14 +224,26 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
void auxtrace_record__free(struct auxtrace_record *itr);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg);
+
int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
int itrace_parse_synth_opts(const struct option *opt, const char *str,
int unset);
void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
static inline int auxtrace__process_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 657dcfa..8ef3725 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -221,6 +221,11 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_MAX
};
+enum auxtrace_error_type {
+ PERF_AUXTRACE_ERROR_ITRACE = 1,
+ PERF_AUXTRACE_ERROR_MAX
+};
+
/*
* The kernel collects the number of events it couldn't send in a stretch and
* when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -245,6 +250,7 @@ struct events_stats {
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
+ u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
};
struct attr_event {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7271c6b..1db3ce1 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1093,6 +1093,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
lseek(fd, file_offset + event->header.size, SEEK_SET);
return tool->auxtrace(tool, event, session);
case PERF_RECORD_AUXTRACE_ERROR:
+ perf_session__auxtrace_error_inc(session, event);
return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
@@ -1282,6 +1283,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
if (oe->nr_unordered_events != 0)
ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+ events_stats__auxtrace_error_warn(stats);
}
volatile int session_done;
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 11/44] perf auxtrace: Add helpers for queuing AUX area tracing data
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (9 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 10/44] perf auxtrace: Add helpers for AUX area tracing errors Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-21 9:21 ` [PATCH V2 " Adrian Hunter
2015-04-09 15:53 ` [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues Adrian Hunter
` (32 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Provide functions to queue AUX area tracing data
buffers for processing. A AUX area decoder
need not use the queues, however Intel BTS and Intel PT
will use them.
There is one queue for each of the mmap buffers that
were used for recording. Because those mmaps were
associated with per-cpu or per-thread contexts, the
data is time-ordered with respect to those contexts.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 305 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 87 +++++++++++++
2 files changed, 392 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9073fe2..78a6bf9 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -22,11 +22,15 @@
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <linux/string.h>
+#include <sys/param.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <limits.h>
#include <errno.h>
+#include <linux/list.h>
#include "../perf.h"
#include "util.h"
@@ -122,6 +126,241 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
}
}
+#define AUXTRACE_INIT_NR_QUEUES 32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+ struct auxtrace_queue *queue_array;
+ unsigned int max_nr_queues, i;
+
+ max_nr_queues = MIN(UINT_MAX, SIZE_MAX) / sizeof(struct auxtrace_queue);
+ if (nr_queues > max_nr_queues)
+ return NULL;
+
+ queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+ if (!queue_array)
+ return NULL;
+
+ for (i = 0; i < nr_queues; i++) {
+ INIT_LIST_HEAD(&queue_array[i].head);
+ queue_array[i].priv = NULL;
+ }
+
+ return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+ queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+ queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+ if (!queues->queue_array)
+ return -ENOMEM;
+ return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+ unsigned int new_nr_queues)
+{
+ unsigned int nr_queues = queues->nr_queues;
+ struct auxtrace_queue *queue_array;
+ unsigned int i;
+
+ if (!nr_queues)
+ nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+ while (nr_queues && nr_queues < new_nr_queues)
+ nr_queues <<= 1;
+
+ if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+ return -EINVAL;
+
+ queue_array = auxtrace_alloc_queue_array(nr_queues);
+ if (!queue_array)
+ return -ENOMEM;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ list_splice_tail(&queues->queue_array[i].head,
+ &queue_array[i].head);
+ queue_array[i].priv = queues->queue_array[i].priv;
+ }
+
+ queues->nr_queues = nr_queues;
+ queues->queue_array = queue_array;
+
+ return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+ int fd = perf_data_file__fd(session->file);
+ void *p;
+ ssize_t ret;
+
+ if (size > SSIZE_MAX)
+ return NULL;
+
+ p = malloc(size);
+ if (!p)
+ return NULL;
+
+ ret = readn(fd, p, size);
+ if (ret != (ssize_t)size) {
+ free(p);
+ return NULL;
+ }
+
+ return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (idx >= queues->nr_queues) {
+ err = auxtrace_queues__grow(queues, idx + 1);
+ if (err)
+ return err;
+ }
+
+ queue = &queues->queue_array[idx];
+
+ if (!queue->set) {
+ queue->set = true;
+ queue->tid = buffer->tid;
+ queue->cpu = buffer->cpu;
+ } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+ pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+ queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+ return -EINVAL;
+ }
+
+ buffer->buffer_nr = queues->next_buffer_nr++;
+
+ list_add_tail(&buffer->list, &queue->head);
+
+ queues->new_data = true;
+ queues->populated = true;
+
+ return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ u64 sz = buffer->size;
+ bool consecutive = false;
+ struct auxtrace_buffer *b;
+ int err;
+
+ while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+ b = memdup(buffer, sizeof(struct auxtrace_buffer));
+ if (!b)
+ return -ENOMEM;
+ b->size = BUFFER_LIMIT_FOR_32_BIT;
+ b->consecutive = consecutive;
+ err = auxtrace_queues__add_buffer(queues, idx, b);
+ if (err) {
+ auxtrace_buffer__free(b);
+ return err;
+ }
+ buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+ sz -= BUFFER_LIMIT_FOR_32_BIT;
+ consecutive = true;
+ }
+
+ buffer->size = sz;
+ buffer->consecutive = consecutive;
+
+ return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ if (session->one_mmap) {
+ buffer->data = buffer->data_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ } else if (perf_data_file__is_pipe(session->file)) {
+ buffer->data = auxtrace_copy_data(buffer->size, session);
+ if (!buffer->data)
+ return -ENOMEM;
+ buffer->data_needs_freeing = true;
+ } else if (BITS_PER_LONG == 32 &&
+ buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+ int err;
+
+ err = auxtrace_queues__split_buffer(queues, idx, buffer);
+ if (err)
+ return err;
+ }
+
+ return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr)
+{
+ struct auxtrace_buffer *buffer;
+ unsigned int idx;
+ int err;
+
+ buffer = zalloc(sizeof(struct auxtrace_buffer));
+ if (!buffer)
+ return -ENOMEM;
+
+ buffer->pid = -1;
+ buffer->tid = event->auxtrace.tid;
+ buffer->cpu = event->auxtrace.cpu;
+ buffer->data_offset = data_offset;
+ buffer->offset = event->auxtrace.offset;
+ buffer->reference = event->auxtrace.reference;
+ buffer->size = event->auxtrace.size;
+ idx = event->auxtrace.idx;
+
+ err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+ if (err)
+ goto out_err;
+
+ if (buffer_ptr)
+ *buffer_ptr = buffer;
+
+ return 0;
+
+out_err:
+ auxtrace_buffer__free(buffer);
+ return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ while (!list_empty(&queues->queue_array[i].head)) {
+ struct auxtrace_buffer *buffer;
+
+ buffer = list_entry(queues->queue_array[i].head.next,
+ struct auxtrace_buffer, list);
+ list_del(&buffer->list);
+ auxtrace_buffer__free(buffer);
+ }
+ }
+
+ zfree(&queues->queue_array);
+ queues->nr_queues = 0;
+}
+
size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
{
if (itr)
@@ -174,6 +413,72 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (buffer) {
+ if (list_is_last(&buffer->list, &queue->head))
+ return NULL;
+ return list_entry(buffer->list.next, struct auxtrace_buffer,
+ list);
+ } else {
+ if (list_empty(&queue->head))
+ return NULL;
+ return list_entry(queue->head.next, struct auxtrace_buffer,
+ list);
+ }
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+ size_t adj = buffer->data_offset & (page_size - 1);
+ size_t size = buffer->size + adj;
+ off_t file_offset = buffer->data_offset - adj;
+ void *addr;
+
+ if (buffer->data)
+ return buffer->data;
+
+ addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+ if (addr == MAP_FAILED)
+ return NULL;
+
+ buffer->mmap_addr = addr;
+ buffer->mmap_size = size;
+
+ buffer->data = addr + adj;
+
+ return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+ if (!buffer->data || !buffer->mmap_addr)
+ return;
+ munmap(buffer->mmap_addr, buffer->mmap_size);
+ buffer->mmap_addr = NULL;
+ buffer->mmap_size = 0;
+ buffer->data = NULL;
+ buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__put_data(buffer);
+ if (buffer->data_needs_freeing) {
+ buffer->data_needs_freeing = false;
+ zfree(&buffer->data);
+ buffer->use_data = NULL;
+ buffer->size = 0;
+ }
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__drop_data(buffer);
+ free(buffer);
+}
+
void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
int code, int cpu, pid_t pid, pid_t tid, u64 ip,
const char *msg)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bcfb928..c6b5981 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -19,6 +19,7 @@
#include <sys/types.h>
#include <stdbool.h>
#include <stddef.h>
+#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
@@ -93,6 +94,80 @@ struct auxtrace {
};
/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ * needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ * to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ * perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ * recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+ struct list_head list;
+ size_t size;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ void *data;
+ off_t data_offset;
+ void *mmap_addr;
+ size_t mmap_size;
+ bool data_needs_freeing;
+ bool consecutive;
+ u64 offset;
+ u64 reference;
+ u64 buffer_nr;
+ size_t use_size;
+ void *use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+ struct list_head head;
+ pid_t tid;
+ int cpu;
+ bool set;
+ void *priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+ struct auxtrace_queue *queue_array;
+ unsigned int nr_queues;
+ bool new_data;
+ bool populated;
+ u64 next_buffer_nr;
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -210,6 +285,18 @@ typedef int (*process_auxtrace_t)(struct perf_tool *tool,
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn);
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH V2 11/44] perf auxtrace: Add helpers for queuing AUX area tracing data
2015-04-09 15:53 ` [PATCH 11/44] perf auxtrace: Add helpers for queuing AUX area tracing data Adrian Hunter
@ 2015-04-21 9:21 ` Adrian Hunter
2015-05-06 3:01 ` [tip:perf/core] " tip-bot for Adrian Hunter
0 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-21 9:21 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Provide functions to queue AUX area tracing data
buffers for processing. A AUX area decoder
need not use the queues, however Intel BTS and Intel PT
will use them.
There is one queue for each of the mmap buffers that
were used for recording. Because those mmaps were
associated with per-cpu or per-thread contexts, the
data is time-ordered with respect to those contexts.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
Changes in V2:
Get rid of MIN()
tools/perf/util/auxtrace.c | 305 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 87 +++++++++++++
2 files changed, 392 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9073fe2..60f0f0d 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -22,11 +22,15 @@
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <linux/string.h>
+#include <sys/param.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <limits.h>
#include <errno.h>
+#include <linux/list.h>
#include "../perf.h"
#include "util.h"
@@ -122,6 +126,241 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
}
}
+#define AUXTRACE_INIT_NR_QUEUES 32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+ struct auxtrace_queue *queue_array;
+ unsigned int max_nr_queues, i;
+
+ max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+ if (nr_queues > max_nr_queues)
+ return NULL;
+
+ queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+ if (!queue_array)
+ return NULL;
+
+ for (i = 0; i < nr_queues; i++) {
+ INIT_LIST_HEAD(&queue_array[i].head);
+ queue_array[i].priv = NULL;
+ }
+
+ return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+ queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+ queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+ if (!queues->queue_array)
+ return -ENOMEM;
+ return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+ unsigned int new_nr_queues)
+{
+ unsigned int nr_queues = queues->nr_queues;
+ struct auxtrace_queue *queue_array;
+ unsigned int i;
+
+ if (!nr_queues)
+ nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+ while (nr_queues && nr_queues < new_nr_queues)
+ nr_queues <<= 1;
+
+ if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+ return -EINVAL;
+
+ queue_array = auxtrace_alloc_queue_array(nr_queues);
+ if (!queue_array)
+ return -ENOMEM;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ list_splice_tail(&queues->queue_array[i].head,
+ &queue_array[i].head);
+ queue_array[i].priv = queues->queue_array[i].priv;
+ }
+
+ queues->nr_queues = nr_queues;
+ queues->queue_array = queue_array;
+
+ return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+ int fd = perf_data_file__fd(session->file);
+ void *p;
+ ssize_t ret;
+
+ if (size > SSIZE_MAX)
+ return NULL;
+
+ p = malloc(size);
+ if (!p)
+ return NULL;
+
+ ret = readn(fd, p, size);
+ if (ret != (ssize_t)size) {
+ free(p);
+ return NULL;
+ }
+
+ return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (idx >= queues->nr_queues) {
+ err = auxtrace_queues__grow(queues, idx + 1);
+ if (err)
+ return err;
+ }
+
+ queue = &queues->queue_array[idx];
+
+ if (!queue->set) {
+ queue->set = true;
+ queue->tid = buffer->tid;
+ queue->cpu = buffer->cpu;
+ } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+ pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+ queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+ return -EINVAL;
+ }
+
+ buffer->buffer_nr = queues->next_buffer_nr++;
+
+ list_add_tail(&buffer->list, &queue->head);
+
+ queues->new_data = true;
+ queues->populated = true;
+
+ return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ u64 sz = buffer->size;
+ bool consecutive = false;
+ struct auxtrace_buffer *b;
+ int err;
+
+ while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+ b = memdup(buffer, sizeof(struct auxtrace_buffer));
+ if (!b)
+ return -ENOMEM;
+ b->size = BUFFER_LIMIT_FOR_32_BIT;
+ b->consecutive = consecutive;
+ err = auxtrace_queues__add_buffer(queues, idx, b);
+ if (err) {
+ auxtrace_buffer__free(b);
+ return err;
+ }
+ buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+ sz -= BUFFER_LIMIT_FOR_32_BIT;
+ consecutive = true;
+ }
+
+ buffer->size = sz;
+ buffer->consecutive = consecutive;
+
+ return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ if (session->one_mmap) {
+ buffer->data = buffer->data_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ } else if (perf_data_file__is_pipe(session->file)) {
+ buffer->data = auxtrace_copy_data(buffer->size, session);
+ if (!buffer->data)
+ return -ENOMEM;
+ buffer->data_needs_freeing = true;
+ } else if (BITS_PER_LONG == 32 &&
+ buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+ int err;
+
+ err = auxtrace_queues__split_buffer(queues, idx, buffer);
+ if (err)
+ return err;
+ }
+
+ return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr)
+{
+ struct auxtrace_buffer *buffer;
+ unsigned int idx;
+ int err;
+
+ buffer = zalloc(sizeof(struct auxtrace_buffer));
+ if (!buffer)
+ return -ENOMEM;
+
+ buffer->pid = -1;
+ buffer->tid = event->auxtrace.tid;
+ buffer->cpu = event->auxtrace.cpu;
+ buffer->data_offset = data_offset;
+ buffer->offset = event->auxtrace.offset;
+ buffer->reference = event->auxtrace.reference;
+ buffer->size = event->auxtrace.size;
+ idx = event->auxtrace.idx;
+
+ err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+ if (err)
+ goto out_err;
+
+ if (buffer_ptr)
+ *buffer_ptr = buffer;
+
+ return 0;
+
+out_err:
+ auxtrace_buffer__free(buffer);
+ return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ while (!list_empty(&queues->queue_array[i].head)) {
+ struct auxtrace_buffer *buffer;
+
+ buffer = list_entry(queues->queue_array[i].head.next,
+ struct auxtrace_buffer, list);
+ list_del(&buffer->list);
+ auxtrace_buffer__free(buffer);
+ }
+ }
+
+ zfree(&queues->queue_array);
+ queues->nr_queues = 0;
+}
+
size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
{
if (itr)
@@ -174,6 +413,72 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (buffer) {
+ if (list_is_last(&buffer->list, &queue->head))
+ return NULL;
+ return list_entry(buffer->list.next, struct auxtrace_buffer,
+ list);
+ } else {
+ if (list_empty(&queue->head))
+ return NULL;
+ return list_entry(queue->head.next, struct auxtrace_buffer,
+ list);
+ }
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+ size_t adj = buffer->data_offset & (page_size - 1);
+ size_t size = buffer->size + adj;
+ off_t file_offset = buffer->data_offset - adj;
+ void *addr;
+
+ if (buffer->data)
+ return buffer->data;
+
+ addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+ if (addr == MAP_FAILED)
+ return NULL;
+
+ buffer->mmap_addr = addr;
+ buffer->mmap_size = size;
+
+ buffer->data = addr + adj;
+
+ return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+ if (!buffer->data || !buffer->mmap_addr)
+ return;
+ munmap(buffer->mmap_addr, buffer->mmap_size);
+ buffer->mmap_addr = NULL;
+ buffer->mmap_size = 0;
+ buffer->data = NULL;
+ buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__put_data(buffer);
+ if (buffer->data_needs_freeing) {
+ buffer->data_needs_freeing = false;
+ zfree(&buffer->data);
+ buffer->use_data = NULL;
+ buffer->size = 0;
+ }
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__drop_data(buffer);
+ free(buffer);
+}
+
void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
int code, int cpu, pid_t pid, pid_t tid, u64 ip,
const char *msg)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bcfb928..c6b5981 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -19,6 +19,7 @@
#include <sys/types.h>
#include <stdbool.h>
#include <stddef.h>
+#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
@@ -93,6 +94,80 @@ struct auxtrace {
};
/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ * needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ * to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ * perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ * recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+ struct list_head list;
+ size_t size;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ void *data;
+ off_t data_offset;
+ void *mmap_addr;
+ size_t mmap_size;
+ bool data_needs_freeing;
+ bool consecutive;
+ u64 offset;
+ u64 reference;
+ u64 buffer_nr;
+ size_t use_size;
+ void *use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+ struct list_head head;
+ pid_t tid;
+ int cpu;
+ bool set;
+ void *priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+ struct auxtrace_queue *queue_array;
+ unsigned int nr_queues;
+ bool new_data;
+ bool populated;
+ u64 next_buffer_nr;
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -210,6 +285,18 @@ typedef int (*process_auxtrace_t)(struct perf_tool *tool,
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn);
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add helpers for queuing AUX area tracing data
2015-04-21 9:21 ` [PATCH V2 " Adrian Hunter
@ 2015-05-06 3:01 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:01 UTC (permalink / raw)
To: linux-tip-commits
Cc: tglx, peterz, fweisbec, hpa, linux-kernel, dsahern, namhyung,
adrian.hunter, eranian, acme, jolsa, mingo
Commit-ID: e502789302a6ece9fa4b9505df234c319bfa0650
Gitweb: http://git.kernel.org/tip/e502789302a6ece9fa4b9505df234c319bfa0650
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 21 Apr 2015 12:21:51 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:54 -0300
perf auxtrace: Add helpers for queuing AUX area tracing data
Provide functions to queue AUX area tracing data buffers for processing.
A AUX area decoder need not use the queues, however Intel BTS and Intel
PT will use them.
There is one queue for each of the mmap buffers that were used for
recording. Because those mmaps were associated with per-cpu or
per-thread contexts, the data is time-ordered with respect to those
contexts.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1429608111-18160-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 305 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 87 +++++++++++++
2 files changed, 392 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 905188b..252417a 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -22,11 +22,15 @@
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <linux/string.h>
+#include <sys/param.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <limits.h>
#include <errno.h>
+#include <linux/list.h>
#include "../perf.h"
#include "util.h"
@@ -122,6 +126,241 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
}
}
+#define AUXTRACE_INIT_NR_QUEUES 32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+ struct auxtrace_queue *queue_array;
+ unsigned int max_nr_queues, i;
+
+ max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+ if (nr_queues > max_nr_queues)
+ return NULL;
+
+ queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+ if (!queue_array)
+ return NULL;
+
+ for (i = 0; i < nr_queues; i++) {
+ INIT_LIST_HEAD(&queue_array[i].head);
+ queue_array[i].priv = NULL;
+ }
+
+ return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+ queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+ queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+ if (!queues->queue_array)
+ return -ENOMEM;
+ return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+ unsigned int new_nr_queues)
+{
+ unsigned int nr_queues = queues->nr_queues;
+ struct auxtrace_queue *queue_array;
+ unsigned int i;
+
+ if (!nr_queues)
+ nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+ while (nr_queues && nr_queues < new_nr_queues)
+ nr_queues <<= 1;
+
+ if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+ return -EINVAL;
+
+ queue_array = auxtrace_alloc_queue_array(nr_queues);
+ if (!queue_array)
+ return -ENOMEM;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ list_splice_tail(&queues->queue_array[i].head,
+ &queue_array[i].head);
+ queue_array[i].priv = queues->queue_array[i].priv;
+ }
+
+ queues->nr_queues = nr_queues;
+ queues->queue_array = queue_array;
+
+ return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+ int fd = perf_data_file__fd(session->file);
+ void *p;
+ ssize_t ret;
+
+ if (size > SSIZE_MAX)
+ return NULL;
+
+ p = malloc(size);
+ if (!p)
+ return NULL;
+
+ ret = readn(fd, p, size);
+ if (ret != (ssize_t)size) {
+ free(p);
+ return NULL;
+ }
+
+ return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (idx >= queues->nr_queues) {
+ err = auxtrace_queues__grow(queues, idx + 1);
+ if (err)
+ return err;
+ }
+
+ queue = &queues->queue_array[idx];
+
+ if (!queue->set) {
+ queue->set = true;
+ queue->tid = buffer->tid;
+ queue->cpu = buffer->cpu;
+ } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+ pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+ queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+ return -EINVAL;
+ }
+
+ buffer->buffer_nr = queues->next_buffer_nr++;
+
+ list_add_tail(&buffer->list, &queue->head);
+
+ queues->new_data = true;
+ queues->populated = true;
+
+ return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ u64 sz = buffer->size;
+ bool consecutive = false;
+ struct auxtrace_buffer *b;
+ int err;
+
+ while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+ b = memdup(buffer, sizeof(struct auxtrace_buffer));
+ if (!b)
+ return -ENOMEM;
+ b->size = BUFFER_LIMIT_FOR_32_BIT;
+ b->consecutive = consecutive;
+ err = auxtrace_queues__add_buffer(queues, idx, b);
+ if (err) {
+ auxtrace_buffer__free(b);
+ return err;
+ }
+ buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+ sz -= BUFFER_LIMIT_FOR_32_BIT;
+ consecutive = true;
+ }
+
+ buffer->size = sz;
+ buffer->consecutive = consecutive;
+
+ return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ if (session->one_mmap) {
+ buffer->data = buffer->data_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ } else if (perf_data_file__is_pipe(session->file)) {
+ buffer->data = auxtrace_copy_data(buffer->size, session);
+ if (!buffer->data)
+ return -ENOMEM;
+ buffer->data_needs_freeing = true;
+ } else if (BITS_PER_LONG == 32 &&
+ buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+ int err;
+
+ err = auxtrace_queues__split_buffer(queues, idx, buffer);
+ if (err)
+ return err;
+ }
+
+ return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr)
+{
+ struct auxtrace_buffer *buffer;
+ unsigned int idx;
+ int err;
+
+ buffer = zalloc(sizeof(struct auxtrace_buffer));
+ if (!buffer)
+ return -ENOMEM;
+
+ buffer->pid = -1;
+ buffer->tid = event->auxtrace.tid;
+ buffer->cpu = event->auxtrace.cpu;
+ buffer->data_offset = data_offset;
+ buffer->offset = event->auxtrace.offset;
+ buffer->reference = event->auxtrace.reference;
+ buffer->size = event->auxtrace.size;
+ idx = event->auxtrace.idx;
+
+ err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+ if (err)
+ goto out_err;
+
+ if (buffer_ptr)
+ *buffer_ptr = buffer;
+
+ return 0;
+
+out_err:
+ auxtrace_buffer__free(buffer);
+ return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ while (!list_empty(&queues->queue_array[i].head)) {
+ struct auxtrace_buffer *buffer;
+
+ buffer = list_entry(queues->queue_array[i].head.next,
+ struct auxtrace_buffer, list);
+ list_del(&buffer->list);
+ auxtrace_buffer__free(buffer);
+ }
+ }
+
+ zfree(&queues->queue_array);
+ queues->nr_queues = 0;
+}
+
size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
{
if (itr)
@@ -174,6 +413,72 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (buffer) {
+ if (list_is_last(&buffer->list, &queue->head))
+ return NULL;
+ return list_entry(buffer->list.next, struct auxtrace_buffer,
+ list);
+ } else {
+ if (list_empty(&queue->head))
+ return NULL;
+ return list_entry(queue->head.next, struct auxtrace_buffer,
+ list);
+ }
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+ size_t adj = buffer->data_offset & (page_size - 1);
+ size_t size = buffer->size + adj;
+ off_t file_offset = buffer->data_offset - adj;
+ void *addr;
+
+ if (buffer->data)
+ return buffer->data;
+
+ addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+ if (addr == MAP_FAILED)
+ return NULL;
+
+ buffer->mmap_addr = addr;
+ buffer->mmap_size = size;
+
+ buffer->data = addr + adj;
+
+ return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+ if (!buffer->data || !buffer->mmap_addr)
+ return;
+ munmap(buffer->mmap_addr, buffer->mmap_size);
+ buffer->mmap_addr = NULL;
+ buffer->mmap_size = 0;
+ buffer->data = NULL;
+ buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__put_data(buffer);
+ if (buffer->data_needs_freeing) {
+ buffer->data_needs_freeing = false;
+ zfree(&buffer->data);
+ buffer->use_data = NULL;
+ buffer->size = 0;
+ }
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__drop_data(buffer);
+ free(buffer);
+}
+
void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
int code, int cpu, pid_t pid, pid_t tid, u64 ip,
const char *msg)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bcfb928..c6b5981 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -19,6 +19,7 @@
#include <sys/types.h>
#include <stdbool.h>
#include <stddef.h>
+#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
@@ -93,6 +94,80 @@ struct auxtrace {
};
/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ * needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ * to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ * perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ * recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+ struct list_head list;
+ size_t size;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ void *data;
+ off_t data_offset;
+ void *mmap_addr;
+ size_t mmap_size;
+ bool data_needs_freeing;
+ bool consecutive;
+ u64 offset;
+ u64 reference;
+ u64 buffer_nr;
+ size_t use_size;
+ void *use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+ struct list_head head;
+ pid_t tid;
+ int cpu;
+ bool set;
+ void *priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+ struct auxtrace_queue *queue_array;
+ unsigned int nr_queues;
+ bool new_data;
+ bool populated;
+ u64 next_buffer_nr;
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -210,6 +285,18 @@ typedef int (*process_auxtrace_t)(struct perf_tool *tool,
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn);
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (10 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 11/44] perf auxtrace: Add helpers for queuing AUX area tracing data Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-21 15:01 ` Arnaldo Carvalho de Melo
2015-05-06 3:01 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 13/44] perf auxtrace: Add processing for AUX area tracing events Adrian Hunter
` (31 subsequent siblings)
43 siblings, 2 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
In order to process AUX area tracing
data in time order, the queue with data
with the lowest timestamp must be
processed first. Provide a heap to
keep track of which queue that is.
As with the queues, a decoder does not have
to use the heap, but Intel BTS and Intel PT
will use it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 29 ++++++++++++++++
2 files changed, 114 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 78a6bf9..c2f060b 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -361,6 +361,91 @@ void auxtrace_queues__free(struct auxtrace_queues *queues)
queues->nr_queues = 0;
}
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+ unsigned int pos, unsigned int queue_nr,
+ u64 ordinal)
+{
+ unsigned int parent;
+
+ while (pos) {
+ parent = (pos - 1) >> 1;
+ if (heap_array[parent].ordinal <= ordinal)
+ break;
+ heap_array[pos] = heap_array[parent];
+ pos = parent;
+ }
+ heap_array[pos].queue_nr = queue_nr;
+ heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal)
+{
+ struct auxtrace_heap_item *heap_array;
+
+ if (queue_nr >= heap->heap_sz) {
+ unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+ while (heap_sz <= queue_nr)
+ heap_sz <<= 1;
+ heap_array = realloc(heap->heap_array,
+ heap_sz * sizeof(struct auxtrace_heap_item));
+ if (!heap_array)
+ return -ENOMEM;
+ heap->heap_array = heap_array;
+ heap->heap_sz = heap_sz;
+ }
+
+ auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+ return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+ zfree(&heap->heap_array);
+ heap->heap_cnt = 0;
+ heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+ unsigned int pos, last, heap_cnt = heap->heap_cnt;
+ struct auxtrace_heap_item *heap_array;
+
+ if (!heap_cnt)
+ return;
+
+ heap->heap_cnt -= 1;
+
+ heap_array = heap->heap_array;
+
+ pos = 0;
+ while (1) {
+ unsigned int left, right;
+
+ left = (pos << 1) + 1;
+ if (left >= heap_cnt)
+ break;
+ right = left + 1;
+ if (right >= heap_cnt) {
+ heap_array[pos] = heap_array[left];
+ return;
+ }
+ if (heap_array[left].ordinal < heap_array[right].ordinal) {
+ heap_array[pos] = heap_array[left];
+ pos = left;
+ } else {
+ heap_array[pos] = heap_array[right];
+ pos = right;
+ }
+ }
+
+ last = heap_cnt - 1;
+ auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+ heap_array[last].ordinal);
+}
+
size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
{
if (itr)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index c6b5981..c3514f3 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -168,6 +168,29 @@ struct auxtrace_queues {
};
/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ * to be a timestamp
+ */
+struct auxtrace_heap_item {
+ unsigned int queue_nr;
+ u64 ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+ struct auxtrace_heap_item *heap_array;
+ unsigned int heap_cnt;
+ unsigned int heap_sz;
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -297,6 +320,12 @@ void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues
2015-04-09 15:53 ` [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues Adrian Hunter
@ 2015-04-21 15:01 ` Arnaldo Carvalho de Melo
2015-05-06 3:01 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-21 15:01 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:52PM +0300, Adrian Hunter escreveu:
> In order to process AUX area tracing
> data in time order, the queue with data
> with the lowest timestamp must be
> processed first. Provide a heap to
> keep track of which queue that is.
>
> As with the queues, a decoder does not have
> to use the heap, but Intel BTS and Intel PT
> will use it.
Just judging from the description, this is like what I think should be
done in 'perf trace', i.e. take advantage of the fact that each perf
mmap buffer is time ordered and go on sorting the various "queues" by
the timestamp on its head, processing from that queue till its timestamp
is after the second most recent queue head timestamp, reinsert the queue
we've been consuming, continue with the second (now first) queue (ring
buffer).
Reading on, perhaps we can reuse this...
- Arnaldo
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
> tools/perf/util/auxtrace.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++
> tools/perf/util/auxtrace.h | 29 ++++++++++++++++
> 2 files changed, 114 insertions(+)
>
> diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
> index 78a6bf9..c2f060b 100644
> --- a/tools/perf/util/auxtrace.c
> +++ b/tools/perf/util/auxtrace.c
> @@ -361,6 +361,91 @@ void auxtrace_queues__free(struct auxtrace_queues *queues)
> queues->nr_queues = 0;
> }
>
> +static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
> + unsigned int pos, unsigned int queue_nr,
> + u64 ordinal)
> +{
> + unsigned int parent;
> +
> + while (pos) {
> + parent = (pos - 1) >> 1;
> + if (heap_array[parent].ordinal <= ordinal)
> + break;
> + heap_array[pos] = heap_array[parent];
> + pos = parent;
> + }
> + heap_array[pos].queue_nr = queue_nr;
> + heap_array[pos].ordinal = ordinal;
> +}
> +
> +int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
> + u64 ordinal)
> +{
> + struct auxtrace_heap_item *heap_array;
> +
> + if (queue_nr >= heap->heap_sz) {
> + unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
> +
> + while (heap_sz <= queue_nr)
> + heap_sz <<= 1;
> + heap_array = realloc(heap->heap_array,
> + heap_sz * sizeof(struct auxtrace_heap_item));
> + if (!heap_array)
> + return -ENOMEM;
> + heap->heap_array = heap_array;
> + heap->heap_sz = heap_sz;
> + }
> +
> + auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
> +
> + return 0;
> +}
> +
> +void auxtrace_heap__free(struct auxtrace_heap *heap)
> +{
> + zfree(&heap->heap_array);
> + heap->heap_cnt = 0;
> + heap->heap_sz = 0;
> +}
> +
> +void auxtrace_heap__pop(struct auxtrace_heap *heap)
> +{
> + unsigned int pos, last, heap_cnt = heap->heap_cnt;
> + struct auxtrace_heap_item *heap_array;
> +
> + if (!heap_cnt)
> + return;
> +
> + heap->heap_cnt -= 1;
> +
> + heap_array = heap->heap_array;
> +
> + pos = 0;
> + while (1) {
> + unsigned int left, right;
> +
> + left = (pos << 1) + 1;
> + if (left >= heap_cnt)
> + break;
> + right = left + 1;
> + if (right >= heap_cnt) {
> + heap_array[pos] = heap_array[left];
> + return;
> + }
> + if (heap_array[left].ordinal < heap_array[right].ordinal) {
> + heap_array[pos] = heap_array[left];
> + pos = left;
> + } else {
> + heap_array[pos] = heap_array[right];
> + pos = right;
> + }
> + }
> +
> + last = heap_cnt - 1;
> + auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
> + heap_array[last].ordinal);
> +}
> +
> size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
> {
> if (itr)
> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
> index c6b5981..c3514f3 100644
> --- a/tools/perf/util/auxtrace.h
> +++ b/tools/perf/util/auxtrace.h
> @@ -168,6 +168,29 @@ struct auxtrace_queues {
> };
>
> /**
> + * struct auxtrace_heap_item - element of struct auxtrace_heap.
> + * @queue_nr: queue number
> + * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
> + * to be a timestamp
> + */
> +struct auxtrace_heap_item {
> + unsigned int queue_nr;
> + u64 ordinal;
> +};
> +
> +/**
> + * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
> + * @heap_array: the heap
> + * @heap_cnt: the number of elements in the heap
> + * @heap_sz: maximum number of elements (grows as needed)
> + */
> +struct auxtrace_heap {
> + struct auxtrace_heap_item *heap_array;
> + unsigned int heap_cnt;
> + unsigned int heap_sz;
> +};
> +
> +/**
> * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
> * @base: address of mapped area
> * @userpg: pointer to buffer's perf_event_mmap_page
> @@ -297,6 +320,12 @@ void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
> void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
> void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
> void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
> +
> +int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
> + u64 ordinal);
> +void auxtrace_heap__pop(struct auxtrace_heap *heap);
> +void auxtrace_heap__free(struct auxtrace_heap *heap);
> +
> struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
> int *err);
>
> --
> 1.9.1
^ permalink raw reply [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add a heap for sorting AUX area tracing queues
2015-04-09 15:53 ` [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues Adrian Hunter
2015-04-21 15:01 ` Arnaldo Carvalho de Melo
@ 2015-05-06 3:01 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:01 UTC (permalink / raw)
To: linux-tip-commits
Cc: linux-kernel, eranian, mingo, peterz, namhyung, jolsa, dsahern,
fweisbec, hpa, tglx, adrian.hunter, acme
Commit-ID: f939715586ea4f046eb52523ae25eb4d20b2a497
Gitweb: http://git.kernel.org/tip/f939715586ea4f046eb52523ae25eb4d20b2a497
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:52 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:54 -0300
perf auxtrace: Add a heap for sorting AUX area tracing queues
In order to process AUX area tracing data in time order, the queue with
data with the lowest timestamp must be processed first. Provide a heap
to keep track of which queue that is.
As with the queues, a decoder does not have to use the heap, but Intel
BTS and Intel PT will use it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-13-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 29 ++++++++++++++++
2 files changed, 114 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 252417a..e13b1a1 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -361,6 +361,91 @@ void auxtrace_queues__free(struct auxtrace_queues *queues)
queues->nr_queues = 0;
}
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+ unsigned int pos, unsigned int queue_nr,
+ u64 ordinal)
+{
+ unsigned int parent;
+
+ while (pos) {
+ parent = (pos - 1) >> 1;
+ if (heap_array[parent].ordinal <= ordinal)
+ break;
+ heap_array[pos] = heap_array[parent];
+ pos = parent;
+ }
+ heap_array[pos].queue_nr = queue_nr;
+ heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal)
+{
+ struct auxtrace_heap_item *heap_array;
+
+ if (queue_nr >= heap->heap_sz) {
+ unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+ while (heap_sz <= queue_nr)
+ heap_sz <<= 1;
+ heap_array = realloc(heap->heap_array,
+ heap_sz * sizeof(struct auxtrace_heap_item));
+ if (!heap_array)
+ return -ENOMEM;
+ heap->heap_array = heap_array;
+ heap->heap_sz = heap_sz;
+ }
+
+ auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+ return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+ zfree(&heap->heap_array);
+ heap->heap_cnt = 0;
+ heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+ unsigned int pos, last, heap_cnt = heap->heap_cnt;
+ struct auxtrace_heap_item *heap_array;
+
+ if (!heap_cnt)
+ return;
+
+ heap->heap_cnt -= 1;
+
+ heap_array = heap->heap_array;
+
+ pos = 0;
+ while (1) {
+ unsigned int left, right;
+
+ left = (pos << 1) + 1;
+ if (left >= heap_cnt)
+ break;
+ right = left + 1;
+ if (right >= heap_cnt) {
+ heap_array[pos] = heap_array[left];
+ return;
+ }
+ if (heap_array[left].ordinal < heap_array[right].ordinal) {
+ heap_array[pos] = heap_array[left];
+ pos = left;
+ } else {
+ heap_array[pos] = heap_array[right];
+ pos = right;
+ }
+ }
+
+ last = heap_cnt - 1;
+ auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+ heap_array[last].ordinal);
+}
+
size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
{
if (itr)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index c6b5981..c3514f3 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -168,6 +168,29 @@ struct auxtrace_queues {
};
/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ * to be a timestamp
+ */
+struct auxtrace_heap_item {
+ unsigned int queue_nr;
+ u64 ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+ struct auxtrace_heap_item *heap_array;
+ unsigned int heap_cnt;
+ unsigned int heap_sz;
+};
+
+/**
* struct auxtrace_mmap - records an mmap of the auxtrace buffer.
* @base: address of mapped area
* @userpg: pointer to buffer's perf_event_mmap_page
@@ -297,6 +320,12 @@ void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 13/44] perf auxtrace: Add processing for AUX area tracing events
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (11 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 12/44] perf auxtrace: Add a heap for sorting AUX area tracing queues Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:01 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 14/44] perf auxtrace: Add a hashtable for caching Adrian Hunter
` (30 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Provide hooks so that an AUX area
decoder can process AUX area tracing
events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 52 +++++++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/auxtrace.h | 13 ++++++++++++
2 files changed, 64 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c2f060b..9cc74ad 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -615,6 +615,53 @@ out_free:
return err;
}
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+ return !session->itrace_synth_opts ||
+ session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ enum auxtrace_type type = event->auxtrace_info.type;
+
+ if (dump_trace)
+ fprintf(stdout, " type: %u\n", type);
+
+ switch (type) {
+ case PERF_AUXTRACE_UNKNOWN:
+ default:
+ return -EINVAL;
+ }
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ s64 err;
+
+ if (dump_trace)
+ fprintf(stdout, " size: %#"PRIx64" offset: %#"PRIx64" ref: %#"PRIx64" idx: %u tid: %d cpu: %d\n",
+ event->auxtrace.size, event->auxtrace.offset,
+ event->auxtrace.reference, event->auxtrace.idx,
+ event->auxtrace.tid, event->auxtrace.cpu);
+
+ if (auxtrace__dont_decode(session))
+ return event->auxtrace.size;
+
+ if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+ return -EINVAL;
+
+ err = session->auxtrace->process_auxtrace_event(session, event, tool);
+ if (err < 0)
+ return err;
+
+ return event->auxtrace.size;
+}
+
#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
#define PERF_ITRACE_DEFAULT_PERIOD 100000
#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
@@ -796,8 +843,11 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
union perf_event *event,
- struct perf_session *session __maybe_unused)
+ struct perf_session *session)
{
+ if (auxtrace__dont_decode(session))
+ return 0;
+
perf_event__fprintf_auxtrace_error(event, stdout);
return 0;
}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index c3514f3..ba78d82 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -36,6 +36,10 @@ struct record_opts;
struct auxtrace_info_event;
struct events_stats;
+enum auxtrace_type {
+ PERF_AUXTRACE_UNKNOWN,
+};
+
enum itrace_period_type {
PERF_ITRACE_PERIOD_INSTRUCTIONS,
PERF_ITRACE_PERIOD_TICKS,
@@ -87,6 +91,9 @@ struct auxtrace {
union perf_event *event,
struct perf_sample *sample,
struct perf_tool *tool);
+ int (*process_auxtrace_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool);
int (*flush_events)(struct perf_session *session,
struct perf_tool *tool);
void (*free_events)(struct perf_session *session);
@@ -348,6 +355,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
int perf_event__process_auxtrace_error(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add processing for AUX area tracing events
2015-04-09 15:53 ` [PATCH 13/44] perf auxtrace: Add processing for AUX area tracing events Adrian Hunter
@ 2015-05-06 3:01 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:01 UTC (permalink / raw)
To: linux-tip-commits
Cc: linux-kernel, hpa, dsahern, acme, eranian, fweisbec, peterz,
mingo, tglx, jolsa, adrian.hunter, namhyung
Commit-ID: 73f75fb1bdc572f97f1eb375f2bbb68cfcba077c
Gitweb: http://git.kernel.org/tip/73f75fb1bdc572f97f1eb375f2bbb68cfcba077c
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:53 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:55 -0300
perf auxtrace: Add processing for AUX area tracing events
Provide hooks so that an AUX area decoder can process AUX area tracing
events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-14-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 52 +++++++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/auxtrace.h | 13 ++++++++++++
2 files changed, 64 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index e13b1a1..c4515e1 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -615,6 +615,53 @@ out_free:
return err;
}
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+ return !session->itrace_synth_opts ||
+ session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ enum auxtrace_type type = event->auxtrace_info.type;
+
+ if (dump_trace)
+ fprintf(stdout, " type: %u\n", type);
+
+ switch (type) {
+ case PERF_AUXTRACE_UNKNOWN:
+ default:
+ return -EINVAL;
+ }
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ s64 err;
+
+ if (dump_trace)
+ fprintf(stdout, " size: %#"PRIx64" offset: %#"PRIx64" ref: %#"PRIx64" idx: %u tid: %d cpu: %d\n",
+ event->auxtrace.size, event->auxtrace.offset,
+ event->auxtrace.reference, event->auxtrace.idx,
+ event->auxtrace.tid, event->auxtrace.cpu);
+
+ if (auxtrace__dont_decode(session))
+ return event->auxtrace.size;
+
+ if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+ return -EINVAL;
+
+ err = session->auxtrace->process_auxtrace_event(session, event, tool);
+ if (err < 0)
+ return err;
+
+ return event->auxtrace.size;
+}
+
#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
#define PERF_ITRACE_DEFAULT_PERIOD 100000
#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
@@ -801,8 +848,11 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
union perf_event *event,
- struct perf_session *session __maybe_unused)
+ struct perf_session *session)
{
+ if (auxtrace__dont_decode(session))
+ return 0;
+
perf_event__fprintf_auxtrace_error(event, stdout);
return 0;
}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index c3514f3..ba78d82 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -36,6 +36,10 @@ struct record_opts;
struct auxtrace_info_event;
struct events_stats;
+enum auxtrace_type {
+ PERF_AUXTRACE_UNKNOWN,
+};
+
enum itrace_period_type {
PERF_ITRACE_PERIOD_INSTRUCTIONS,
PERF_ITRACE_PERIOD_TICKS,
@@ -87,6 +91,9 @@ struct auxtrace {
union perf_event *event,
struct perf_sample *sample,
struct perf_tool *tool);
+ int (*process_auxtrace_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool);
int (*flush_events)(struct perf_session *session,
struct perf_tool *tool);
void (*free_events)(struct perf_session *session);
@@ -348,6 +355,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
int perf_event__process_auxtrace_error(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 14/44] perf auxtrace: Add a hashtable for caching
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (12 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 13/44] perf auxtrace: Add processing for AUX area tracing events Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:02 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 15/44] perf tools: Add member to struct dso for an instruction cache Adrian Hunter
` (29 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Decoding AUX area data may involve walking object
code. Rather than repetitively decoding the same
instructions, a cache can be used to cache the results.
This patch implements a fairly generic hashtable
with a 32-bit key that could be used for other
purposes as well.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 123 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 14 ++++++
2 files changed, 137 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9cc74ad..434e394 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -40,6 +40,8 @@
#include "asm/bug.h"
#include "auxtrace.h"
+#include <linux/hash.h>
+
#include "event.h"
#include "session.h"
#include "debug.h"
@@ -939,3 +941,124 @@ int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
return 1;
}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ * is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+ struct hlist_head *hashtable;
+ size_t sz;
+ size_t entry_size;
+ size_t limit;
+ size_t cnt;
+ unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent)
+{
+ struct auxtrace_cache *c;
+ struct hlist_head *ht;
+ size_t sz, i;
+
+ c = zalloc(sizeof(struct auxtrace_cache));
+ if (!c)
+ return NULL;
+
+ sz = 1UL << bits;
+
+ ht = calloc(sz, sizeof(struct hlist_head));
+ if (!ht)
+ goto out_free;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+
+ c->hashtable = ht;
+ c->sz = sz;
+ c->entry_size = entry_size;
+ c->limit = (c->sz * limit_percent) / 100;
+ c->bits = bits;
+
+ return c;
+
+out_free:
+ free(c);
+ return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_node *tmp;
+ size_t i;
+
+ if (!c)
+ return;
+
+ for (i = 0; i < c->sz; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+ hlist_del(&entry->hash);
+ auxtrace_cache__free_entry(c, entry);
+ }
+ }
+
+ c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+ if (!c)
+ return;
+
+ auxtrace_cache__drop(c);
+ free(c->hashtable);
+ free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+ return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+ void *entry)
+{
+ free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry)
+{
+ if (c->limit && ++c->cnt > c->limit)
+ auxtrace_cache__drop(c);
+
+ entry->key = key;
+ hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+ return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_head *hlist;
+
+ if (!c)
+ return NULL;
+
+ hlist = &c->hashtable[hash_32(key, c->bits)];
+ hlist_for_each_entry(entry, hlist, hash) {
+ if (entry->key == key)
+ return entry;
+ }
+
+ return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index ba78d82..53b60a6 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -333,6 +333,20 @@ int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
void auxtrace_heap__pop(struct auxtrace_heap *heap);
void auxtrace_heap__free(struct auxtrace_heap *heap);
+struct auxtrace_cache_entry {
+ struct hlist_node hash;
+ u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf auxtrace: Add a hashtable for caching
2015-04-09 15:53 ` [PATCH 14/44] perf auxtrace: Add a hashtable for caching Adrian Hunter
@ 2015-05-06 3:02 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:02 UTC (permalink / raw)
To: linux-tip-commits
Cc: dsahern, hpa, peterz, eranian, adrian.hunter, mingo, fweisbec,
jolsa, acme, linux-kernel, namhyung, tglx
Commit-ID: c3278f0231e833c6030c3aeab510415fdbbfd353
Gitweb: http://git.kernel.org/tip/c3278f0231e833c6030c3aeab510415fdbbfd353
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:54 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:55 -0300
perf auxtrace: Add a hashtable for caching
Decoding AUX area data may involve walking object code. Rather than
repetitively decoding the same instructions, a cache can be used to
cache the results.
This patch implements a fairly generic hashtable with a 32-bit key that
could be used for other purposes as well.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-15-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 123 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 14 ++++++
2 files changed, 137 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4515e1..3cd89ec 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -40,6 +40,8 @@
#include "asm/bug.h"
#include "auxtrace.h"
+#include <linux/hash.h>
+
#include "event.h"
#include "session.h"
#include "debug.h"
@@ -944,3 +946,124 @@ int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
return 1;
}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ * is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+ struct hlist_head *hashtable;
+ size_t sz;
+ size_t entry_size;
+ size_t limit;
+ size_t cnt;
+ unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent)
+{
+ struct auxtrace_cache *c;
+ struct hlist_head *ht;
+ size_t sz, i;
+
+ c = zalloc(sizeof(struct auxtrace_cache));
+ if (!c)
+ return NULL;
+
+ sz = 1UL << bits;
+
+ ht = calloc(sz, sizeof(struct hlist_head));
+ if (!ht)
+ goto out_free;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+
+ c->hashtable = ht;
+ c->sz = sz;
+ c->entry_size = entry_size;
+ c->limit = (c->sz * limit_percent) / 100;
+ c->bits = bits;
+
+ return c;
+
+out_free:
+ free(c);
+ return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_node *tmp;
+ size_t i;
+
+ if (!c)
+ return;
+
+ for (i = 0; i < c->sz; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+ hlist_del(&entry->hash);
+ auxtrace_cache__free_entry(c, entry);
+ }
+ }
+
+ c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+ if (!c)
+ return;
+
+ auxtrace_cache__drop(c);
+ free(c->hashtable);
+ free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+ return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+ void *entry)
+{
+ free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry)
+{
+ if (c->limit && ++c->cnt > c->limit)
+ auxtrace_cache__drop(c);
+
+ entry->key = key;
+ hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+ return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_head *hlist;
+
+ if (!c)
+ return NULL;
+
+ hlist = &c->hashtable[hash_32(key, c->bits)];
+ hlist_for_each_entry(entry, hlist, hash) {
+ if (entry->key == key)
+ return entry;
+ }
+
+ return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index ba78d82..53b60a6 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -333,6 +333,20 @@ int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
void auxtrace_heap__pop(struct auxtrace_heap *heap);
void auxtrace_heap__free(struct auxtrace_heap *heap);
+struct auxtrace_cache_entry {
+ struct hlist_node hash;
+ u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 15/44] perf tools: Add member to struct dso for an instruction cache
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (13 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 14/44] perf auxtrace: Add a hashtable for caching Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:02 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 16/44] perf script: Add Instruction Tracing support Adrian Hunter
` (28 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add a member to struct dso that can be used by Instruction
Trace implementations to hold a cache for decoded instructions.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/dso.c | 2 ++
tools/perf/util/dso.h | 3 +++
2 files changed, 5 insertions(+)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd5..13d9ae0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
#include "symbol.h"
#include "dso.h"
#include "machine.h"
+#include "auxtrace.h"
#include "util.h"
#include "debug.h"
@@ -961,6 +962,7 @@ void dso__delete(struct dso *dso)
}
dso__data_close(dso);
+ auxtrace_cache__free(dso->auxtrace_cache);
dso_cache__free(&dso->data.cache);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4..3d79c74 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -126,6 +126,8 @@ struct dsos {
struct rb_root root; /* rbtree root sorted by long name */
};
+struct auxtrace_cache;
+
struct dso {
struct list_head node;
struct rb_node rb_node; /* rbtree node sorted by long name */
@@ -156,6 +158,7 @@ struct dso {
u16 long_name_len;
u16 short_name_len;
void *dwfl; /* DWARF debug info */
+ struct auxtrace_cache *auxtrace_cache;
/* dso data file */
struct {
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf tools: Add member to struct dso for an instruction cache
2015-04-09 15:53 ` [PATCH 15/44] perf tools: Add member to struct dso for an instruction cache Adrian Hunter
@ 2015-05-06 3:02 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:02 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, adrian.hunter, dsahern, linux-kernel, acme, fweisbec,
mingo, jolsa, tglx, hpa, peterz, namhyung
Commit-ID: cfe9174fcfe28f0f73dce422e3151991ee0d49bf
Gitweb: http://git.kernel.org/tip/cfe9174fcfe28f0f73dce422e3151991ee0d49bf
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:55 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:56 -0300
perf tools: Add member to struct dso for an instruction cache
Add a member to struct dso that can be used by Instruction Trace
implementations to hold a cache for decoded instructions.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-16-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/dso.c | 2 ++
tools/perf/util/dso.h | 3 +++
2 files changed, 5 insertions(+)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd5..13d9ae0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
#include "symbol.h"
#include "dso.h"
#include "machine.h"
+#include "auxtrace.h"
#include "util.h"
#include "debug.h"
@@ -961,6 +962,7 @@ void dso__delete(struct dso *dso)
}
dso__data_close(dso);
+ auxtrace_cache__free(dso->auxtrace_cache);
dso_cache__free(&dso->data.cache);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4..3d79c74 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -126,6 +126,8 @@ struct dsos {
struct rb_root root; /* rbtree root sorted by long name */
};
+struct auxtrace_cache;
+
struct dso {
struct list_head node;
struct rb_node rb_node; /* rbtree node sorted by long name */
@@ -156,6 +158,7 @@ struct dso {
u16 long_name_len;
u16 short_name_len;
void *dwfl; /* DWARF debug info */
+ struct auxtrace_cache *auxtrace_cache;
/* dso data file */
struct {
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 16/44] perf script: Add Instruction Tracing support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (14 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 15/44] perf tools: Add member to struct dso for an instruction cache Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-05-06 3:02 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:53 ` [PATCH 17/44] perf script: Always allow fields 'addr' and 'cpu' for auxtrace Adrian Hunter
` (27 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding an AUX area assuming
it contains instruction tracing data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-script.txt | 28 ++++++++++++++++++++++++++++
tools/perf/builtin-script.c | 11 +++++++++++
2 files changed, 39 insertions(+)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 7944575..0befc9c 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -221,6 +221,34 @@ OPTIONS
--header-only
Show only perf.data header.
+-Z::
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain for instructions events
+
+ The default is all events i.e. the same as -Zibe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions
+ events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 58f10b8..b72adfe 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -16,6 +16,7 @@
#include "util/evsel.h"
#include "util/sort.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <linux/bitmap.h>
static char const *script_name;
@@ -1497,6 +1498,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = {0};
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
@@ -1511,6 +1513,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
.attr = process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
+ .auxtrace_error = perf_event__process_auxtrace_error,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -1570,6 +1576,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
"Show the mmap events"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG('Z', "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
@@ -1765,6 +1774,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
script.session = session;
+ session->itrace_synth_opts = &itrace_synth_opts;
+
if (cpu_list) {
err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
if (err < 0)
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf script: Add Instruction Tracing support
2015-04-09 15:53 ` [PATCH 16/44] perf script: Add Instruction Tracing support Adrian Hunter
@ 2015-05-06 3:02 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:02 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, mingo, linux-kernel, namhyung, fweisbec, eranian, hpa,
peterz, dsahern, jolsa, adrian.hunter, tglx
Commit-ID: 7a680eb990b6646ecadf22dca7ded16a33f731b9
Gitweb: http://git.kernel.org/tip/7a680eb990b6646ecadf22dca7ded16a33f731b9
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:53:56 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:56 -0300
perf script: Add Instruction Tracing support
Add support for decoding an AUX area assuming it contains instruction
tracing data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-17-git-send-email-adrian.hunter@intel.com
[ Do not use -Z as an alternative to --itrace ]
[ Fixed initialization of itrace_synth_opts struct fields on older gcc versions ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-script.txt | 27 +++++++++++++++++++++++++++
tools/perf/builtin-script.c | 11 +++++++++++
2 files changed, 38 insertions(+)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 7944575..05df648 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -221,6 +221,33 @@ OPTIONS
--header-only
Show only perf.data header.
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain for instructions events
+
+ The default is all events i.e. the same as --itrace=ibe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions
+ events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 58f10b8..7682665 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -16,6 +16,7 @@
#include "util/evsel.h"
#include "util/sort.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <linux/bitmap.h>
static char const *script_name;
@@ -1497,6 +1498,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = { .set = false, };
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
@@ -1511,6 +1513,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
.attr = process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
+ .auxtrace_error = perf_event__process_auxtrace_error,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -1570,6 +1576,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
"Show the mmap events"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
@@ -1765,6 +1774,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
script.session = session;
+ session->itrace_synth_opts = &itrace_synth_opts;
+
if (cpu_list) {
err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
if (err < 0)
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 17/44] perf script: Always allow fields 'addr' and 'cpu' for auxtrace
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (15 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 16/44] perf script: Add Instruction Tracing support Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-09 15:53 ` [PATCH 18/44] perf report: Add Instruction Tracing support Adrian Hunter
` (26 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
If a file contains AUX area tracing data then always allow
fields 'addr' and 'cpu' to be selected as options for perf
script. This is necessary because AUX area decoding
may synthesize events with that information.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-script.c | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b72adfe..7346045 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -147,9 +147,10 @@ static const char *output_field2str(enum perf_output_field field)
#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x)
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
- u64 sample_type, const char *sample_msg,
- enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field,
+ bool allow_user_set)
{
struct perf_event_attr *attr = &evsel->attr;
int type = attr->type;
@@ -159,6 +160,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
return 0;
if (output[type].user_set) {
+ if (allow_user_set)
+ return 0;
evname = perf_evsel__name(evsel);
pr_err("Samples for '%s' event do not have %s attribute set. "
"Cannot print '%s' field.\n",
@@ -176,10 +179,22 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
return 0;
}
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field)
+{
+ return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+ false);
+}
+
static int perf_evsel__check_attr(struct perf_evsel *evsel,
struct perf_session *session)
{
struct perf_event_attr *attr = &evsel->attr;
+ bool allow_user_set;
+
+ allow_user_set = perf_header__has_feat(&session->header,
+ HEADER_AUXTRACE);
if (PRINT_FIELD(TRACE) &&
!perf_session__has_traces(session, "record -R"))
@@ -192,8 +207,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
}
if (PRINT_FIELD(ADDR) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
- PERF_OUTPUT_ADDR))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+ PERF_OUTPUT_ADDR, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -230,8 +245,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
return -EINVAL;
if (PRINT_FIELD(CPU) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
- PERF_OUTPUT_CPU))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+ PERF_OUTPUT_CPU, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(PERIOD) &&
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 18/44] perf report: Add Instruction Tracing support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (16 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 17/44] perf script: Always allow fields 'addr' and 'cpu' for auxtrace Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-23 14:16 ` Arnaldo Carvalho de Melo
2015-04-09 15:53 ` [PATCH 19/44] perf inject: Re-pipe AUX area tracing events Adrian Hunter
` (25 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding an AUX area assuming
it contains instruction tracing data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-report.txt | 28 ++++++++++++++++++++++++++++
tools/perf/builtin-report.c | 11 +++++++++++
2 files changed, 39 insertions(+)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 4879cf6..66e3df3 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -323,6 +323,34 @@ OPTIONS
--header-only::
Show only perf.data header (forces --stdio).
+-Z::
+--itrace::
+ Options for decoding AUX area tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain for instructions events
+
+ The default is all events i.e. the same as -Zibe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions
+ events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 476cdf7..625c913 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,6 +36,8 @@
#include "util/data.h"
#include "arch/common.h"
+#include "util/auxtrace.h"
+
#include <dlfcn.h>
#include <linux/bitmap.h>
@@ -585,6 +587,7 @@ parse_percent_limit(const struct option *opt, const char *str,
int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = {0};
struct stat st;
bool has_br_stack = false;
int branch_mode = -1;
@@ -607,6 +610,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
.attr = perf_event__process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -717,6 +723,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"Don't show entries under that percent", parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"how to display percentage of filtered entries", parse_filter_percentage),
+ OPT_CALLBACK_OPTARG('Z', "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
struct perf_data_file file = {
@@ -761,6 +770,8 @@ repeat:
report.queue_size);
}
+ session->itrace_synth_opts = &itrace_synth_opts;
+
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* Re: [PATCH 18/44] perf report: Add Instruction Tracing support
2015-04-09 15:53 ` [PATCH 18/44] perf report: Add Instruction Tracing support Adrian Hunter
@ 2015-04-23 14:16 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 79+ messages in thread
From: Arnaldo Carvalho de Melo @ 2015-04-23 14:16 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Stephane Eranian
Em Thu, Apr 09, 2015 at 06:53:58PM +0300, Adrian Hunter escreveu:
> +++ b/tools/perf/Documentation/perf-report.txt
> @@ -323,6 +323,34 @@ OPTIONS
> --header-only::
> Show only perf.data header (forces --stdio).
>
> +-Z::
> +--itrace::
> + Options for decoding AUX area tracing data. The options are:
<SNIP>
> "how to display percentage of filtered entries", parse_filter_percentage),
> + OPT_CALLBACK_OPTARG('Z', "itrace", &itrace_synth_opts, NULL, "opts",
> + "Instruction Tracing options",
> + itrace_parse_synth_opts),
I am also making this be
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
I.e. single letter options should be used for something more
mainstrean/frequently used, and we can also shorten it, so far, to --it:
[acme@ssdandy linux]$ perf script --i
Error: Ambiguous option: i (could be --input or --itrace)
usage: perf script [<options>]
or: perf script [<options>] record <script> [<record-options>] <command>
or: perf script [<options>] report <script> [script-args]
or: perf script [<options>] <script> [<record-options>] <command>
or: perf script [<options>] <top-script> [script-args]
[acme@ssdandy linux]$ perf script --it
failed to open perf.data: Permission denied
- Arnaldo
^ permalink raw reply [flat|nested] 79+ messages in thread
* [PATCH 19/44] perf inject: Re-pipe AUX area tracing events
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (17 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 18/44] perf report: Add Instruction Tracing support Adrian Hunter
@ 2015-04-09 15:53 ` Adrian Hunter
2015-04-21 9:21 ` [PATCH V2 " Adrian Hunter
2015-04-09 15:54 ` [PATCH 20/44] perf inject: Add Instruction Tracing support Adrian Hunter
` (24 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:53 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
New AUX area tracing events must be re-piped by default.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-inject.c | 63 +++++++++++++++++++++++++++++++++++++++++----
1 file changed, 58 insertions(+), 5 deletions(-)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7..d4cfa84 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,14 +38,11 @@ struct event_entry {
union perf_event event[0];
};
-static int perf_event__repipe_synth(struct perf_tool *tool,
- union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
- struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
ssize_t size;
- size = perf_data_file__write(&inject->output, event,
- event->header.size);
+ size = perf_data_file__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
@@ -53,6 +50,34 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
return 0;
}
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, MIN(size, sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
+static int perf_event__repipe_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+
+ return output_bytes(inject, event, event->header.size);
+}
+
static int perf_event__repipe_oe_synth(struct perf_tool *tool,
union perf_event *event,
struct ordered_events *oe __maybe_unused)
@@ -86,6 +111,31 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
return perf_event__repipe_synth(tool, event);
}
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+ int ret;
+
+ if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ ret = output_bytes(inject, event, event->header.size);
+ if (ret < 0)
+ return ret;
+ ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ event->auxtrace.size);
+ } else {
+ ret = output_bytes(inject, event,
+ event->header.size + event->auxtrace.size);
+ }
+ if (ret < 0)
+ return ret;
+
+ return event->auxtrace.size;
+}
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -413,6 +463,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.tracing_data = perf_event__repipe_op2_synth,
+ .auxtrace_info = perf_event__repipe_op2_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
+ .auxtrace_error = perf_event__repipe_op2_synth,
.finished_round = perf_event__repipe_oe_synth,
.build_id = perf_event__repipe_op2_synth,
.id_index = perf_event__repipe_op2_synth,
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH V2 19/44] perf inject: Re-pipe AUX area tracing events
2015-04-09 15:53 ` [PATCH 19/44] perf inject: Re-pipe AUX area tracing events Adrian Hunter
@ 2015-04-21 9:21 ` Adrian Hunter
2015-05-06 3:03 ` [tip:perf/core] " tip-bot for Adrian Hunter
0 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-21 9:21 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
New AUX area tracing events must be re-piped by default.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
Changes in V2:
Get rid of MIN()
tools/perf/builtin-inject.c | 63 +++++++++++++++++++++++++++++++++++++++++----
1 file changed, 58 insertions(+), 5 deletions(-)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7..8f4cad7 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,14 +38,11 @@ struct event_entry {
union perf_event event[0];
};
-static int perf_event__repipe_synth(struct perf_tool *tool,
- union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
- struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
ssize_t size;
- size = perf_data_file__write(&inject->output, event,
- event->header.size);
+ size = perf_data_file__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
@@ -53,6 +50,34 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
return 0;
}
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
+static int perf_event__repipe_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+
+ return output_bytes(inject, event, event->header.size);
+}
+
static int perf_event__repipe_oe_synth(struct perf_tool *tool,
union perf_event *event,
struct ordered_events *oe __maybe_unused)
@@ -86,6 +111,31 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
return perf_event__repipe_synth(tool, event);
}
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+ int ret;
+
+ if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ ret = output_bytes(inject, event, event->header.size);
+ if (ret < 0)
+ return ret;
+ ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ event->auxtrace.size);
+ } else {
+ ret = output_bytes(inject, event,
+ event->header.size + event->auxtrace.size);
+ }
+ if (ret < 0)
+ return ret;
+
+ return event->auxtrace.size;
+}
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -413,6 +463,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.tracing_data = perf_event__repipe_op2_synth,
+ .auxtrace_info = perf_event__repipe_op2_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
+ .auxtrace_error = perf_event__repipe_op2_synth,
.finished_round = perf_event__repipe_oe_synth,
.build_id = perf_event__repipe_op2_synth,
.id_index = perf_event__repipe_op2_synth,
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf inject: Re-pipe AUX area tracing events
2015-04-21 9:21 ` [PATCH V2 " Adrian Hunter
@ 2015-05-06 3:03 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:03 UTC (permalink / raw)
To: linux-tip-commits
Cc: jolsa, hpa, peterz, dsahern, fweisbec, linux-kernel, tglx, acme,
mingo, namhyung, eranian, adrian.hunter
Commit-ID: cd17a9b54463970a47fec33d94f220950c9990c4
Gitweb: http://git.kernel.org/tip/cd17a9b54463970a47fec33d94f220950c9990c4
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 21 Apr 2015 12:21:54 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:57 -0300
perf inject: Re-pipe AUX area tracing events
New AUX area tracing events must be re-piped by default.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1429608114-18194-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-inject.c | 63 +++++++++++++++++++++++++++++++++++++++++----
1 file changed, 58 insertions(+), 5 deletions(-)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7..8f4cad7 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,14 +38,11 @@ struct event_entry {
union perf_event event[0];
};
-static int perf_event__repipe_synth(struct perf_tool *tool,
- union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
- struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
ssize_t size;
- size = perf_data_file__write(&inject->output, event,
- event->header.size);
+ size = perf_data_file__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
@@ -53,6 +50,34 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
return 0;
}
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
+static int perf_event__repipe_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+
+ return output_bytes(inject, event, event->header.size);
+}
+
static int perf_event__repipe_oe_synth(struct perf_tool *tool,
union perf_event *event,
struct ordered_events *oe __maybe_unused)
@@ -86,6 +111,31 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
return perf_event__repipe_synth(tool, event);
}
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+ int ret;
+
+ if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ ret = output_bytes(inject, event, event->header.size);
+ if (ret < 0)
+ return ret;
+ ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ event->auxtrace.size);
+ } else {
+ ret = output_bytes(inject, event,
+ event->header.size + event->auxtrace.size);
+ }
+ if (ret < 0)
+ return ret;
+
+ return event->auxtrace.size;
+}
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -413,6 +463,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.tracing_data = perf_event__repipe_op2_synth,
+ .auxtrace_info = perf_event__repipe_op2_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
+ .auxtrace_error = perf_event__repipe_op2_synth,
.finished_round = perf_event__repipe_oe_synth,
.build_id = perf_event__repipe_op2_synth,
.id_index = perf_event__repipe_op2_synth,
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 20/44] perf inject: Add Instruction Tracing support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (18 preceding siblings ...)
2015-04-09 15:53 ` [PATCH 19/44] perf inject: Re-pipe AUX area tracing events Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-05-06 3:03 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:54 ` [PATCH 21/44] perf tools: Add AUX area tracing index Adrian Hunter
` (23 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding an AUX area assuming
it contains instruction tracing data. The
AUX area tracing events are stripped and replaced
by synthesized events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-inject.txt | 27 ++++++++++++
tools/perf/builtin-inject.c | 71 +++++++++++++++++++++++++++++++-
2 files changed, 96 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index dc7442c..4465519 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -44,6 +44,33 @@ OPTIONS
--kallsyms=<file>::
kallsyms pathname
+-Z::
+--itrace::
+ Decode Instruction Tracing data, replacing it with synthesized events.
+ Options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain for instructions events
+
+ The default is all events i.e. the same as -Zibe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions
+ events can be specified.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index d4cfa84..fc22249 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,6 +16,7 @@
#include "util/debug.h"
#include "util/build-id.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include "util/parse-options.h"
@@ -30,6 +31,7 @@ struct perf_inject {
struct perf_data_file output;
u64 bytes_written;
struct list_head samples;
+ struct itrace_synth_opts itrace_synth_opts;
};
struct event_entry {
@@ -205,6 +207,32 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
return err;
}
+static int perf_event__repipe_comm(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_comm(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_exit(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_tracing_data(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session)
@@ -217,6 +245,18 @@ static int perf_event__repipe_tracing_data(struct perf_tool *tool,
return err;
}
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ int err;
+
+ perf_event__repipe_synth(tool, event);
+ err = perf_event__process_id_index(tool, event, session);
+
+ return err;
+}
+
static int dso__read_build_id(struct dso *dso)
{
if (dso->has_build_id)
@@ -401,16 +441,20 @@ static int __cmd_inject(struct perf_inject *inject)
struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
int fd = perf_data_file__fd(file_out);
+ u64 output_data_offset;
signal(SIGINT, sig_handler);
- if (inject->build_ids || inject->sched_stat) {
+ if (inject->build_ids || inject->sched_stat ||
+ inject->itrace_synth_opts.set) {
inject->tool.mmap = perf_event__repipe_mmap;
inject->tool.mmap2 = perf_event__repipe_mmap2;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
+ output_data_offset = session->header.data_offset;
+
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
} else if (inject->sched_stat) {
@@ -429,10 +473,22 @@ static int __cmd_inject(struct perf_inject *inject)
else if (!strncmp(name, "sched:sched_stat_", 17))
evsel->handler = perf_inject__sched_stat;
}
+ } else if (inject->itrace_synth_opts.set) {
+ session->itrace_synth_opts = &inject->itrace_synth_opts;
+ inject->itrace_synth_opts.inject = true;
+ inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.exit = perf_event__repipe_exit;
+ inject->tool.id_index = perf_event__repipe_id_index;
+ inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
+ inject->tool.auxtrace = perf_event__process_auxtrace;
+ inject->tool.ordered_events = true;
+ inject->tool.ordering_requires_timestamps = true;
+ /* Allow space in the header for new attributes */
+ output_data_offset = 4096;
}
if (!file_out->is_pipe)
- lseek(fd, session->header.data_offset, SEEK_SET);
+ lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
@@ -440,6 +496,14 @@ static int __cmd_inject(struct perf_inject *inject)
if (inject->build_ids)
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
+ /*
+ * The AUX areas have been removed and replaced with
+ * synthesized hardware events, so clear the feature flag.
+ */
+ if (inject->itrace_synth_opts.set)
+ perf_header__clear_feat(&session->header,
+ HEADER_AUXTRACE);
+ session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, fd, true);
}
@@ -497,6 +561,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
"kallsyms pathname"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG('Z', "itrace", &inject.itrace_synth_opts,
+ NULL, "opts", "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const inject_usage[] = {
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf inject: Add Instruction Tracing support
2015-04-09 15:54 ` [PATCH 20/44] perf inject: Add Instruction Tracing support Adrian Hunter
@ 2015-05-06 3:03 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:03 UTC (permalink / raw)
To: linux-tip-commits
Cc: namhyung, tglx, jolsa, adrian.hunter, dsahern, mingo, acme, hpa,
eranian, linux-kernel, peterz, fweisbec
Commit-ID: 0f0aa5e0693ce4000a7657cc47ce4f32b86b91ba
Gitweb: http://git.kernel.org/tip/0f0aa5e0693ce4000a7657cc47ce4f32b86b91ba
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:54:00 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:57 -0300
perf inject: Add Instruction Tracing support
Add support for decoding an AUX area assuming it contains instruction
tracing data. The AUX area tracing events are stripped and replaced by
synthesized events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-21-git-send-email-adrian.hunter@intel.com
[ Do not use -Z as an alternative to --itrace ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-inject.txt | 26 ++++++++++++
tools/perf/builtin-inject.c | 71 +++++++++++++++++++++++++++++++-
2 files changed, 95 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index dc7442c..bb1f655 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -44,6 +44,32 @@ OPTIONS
--kallsyms=<file>::
kallsyms pathname
+--itrace::
+ Decode Instruction Tracing data, replacing it with synthesized events.
+ Options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain for instructions events
+
+ The default is all events i.e. the same as --itrace=ibe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions
+ events can be specified.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8f4cad7..c5f6515 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,6 +16,7 @@
#include "util/debug.h"
#include "util/build-id.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include "util/parse-options.h"
@@ -30,6 +31,7 @@ struct perf_inject {
struct perf_data_file output;
u64 bytes_written;
struct list_head samples;
+ struct itrace_synth_opts itrace_synth_opts;
};
struct event_entry {
@@ -205,6 +207,32 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
return err;
}
+static int perf_event__repipe_comm(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_comm(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_exit(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_tracing_data(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session)
@@ -217,6 +245,18 @@ static int perf_event__repipe_tracing_data(struct perf_tool *tool,
return err;
}
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ int err;
+
+ perf_event__repipe_synth(tool, event);
+ err = perf_event__process_id_index(tool, event, session);
+
+ return err;
+}
+
static int dso__read_build_id(struct dso *dso)
{
if (dso->has_build_id)
@@ -401,16 +441,20 @@ static int __cmd_inject(struct perf_inject *inject)
struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
int fd = perf_data_file__fd(file_out);
+ u64 output_data_offset;
signal(SIGINT, sig_handler);
- if (inject->build_ids || inject->sched_stat) {
+ if (inject->build_ids || inject->sched_stat ||
+ inject->itrace_synth_opts.set) {
inject->tool.mmap = perf_event__repipe_mmap;
inject->tool.mmap2 = perf_event__repipe_mmap2;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
+ output_data_offset = session->header.data_offset;
+
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
} else if (inject->sched_stat) {
@@ -429,10 +473,22 @@ static int __cmd_inject(struct perf_inject *inject)
else if (!strncmp(name, "sched:sched_stat_", 17))
evsel->handler = perf_inject__sched_stat;
}
+ } else if (inject->itrace_synth_opts.set) {
+ session->itrace_synth_opts = &inject->itrace_synth_opts;
+ inject->itrace_synth_opts.inject = true;
+ inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.exit = perf_event__repipe_exit;
+ inject->tool.id_index = perf_event__repipe_id_index;
+ inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
+ inject->tool.auxtrace = perf_event__process_auxtrace;
+ inject->tool.ordered_events = true;
+ inject->tool.ordering_requires_timestamps = true;
+ /* Allow space in the header for new attributes */
+ output_data_offset = 4096;
}
if (!file_out->is_pipe)
- lseek(fd, session->header.data_offset, SEEK_SET);
+ lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
@@ -440,6 +496,14 @@ static int __cmd_inject(struct perf_inject *inject)
if (inject->build_ids)
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
+ /*
+ * The AUX areas have been removed and replaced with
+ * synthesized hardware events, so clear the feature flag.
+ */
+ if (inject->itrace_synth_opts.set)
+ perf_header__clear_feat(&session->header,
+ HEADER_AUXTRACE);
+ session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, fd, true);
}
@@ -497,6 +561,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
"kallsyms pathname"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
+ NULL, "opts", "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const inject_usage[] = {
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 21/44] perf tools: Add AUX area tracing index
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (19 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 20/44] perf inject: Add Instruction Tracing support Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 22/44] perf tools: Hit all build ids when AUX area tracing Adrian Hunter
` (22 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add an index of AUX area tracing events within
a perf.data file.
perf record uses a special user event
PERF_RECORD_FINISHED_ROUND to enable sorting of
events in chunks instead of having to sort all
events altogether.
AUX area tracing events contain data that can
span back to the very beginning of the recording
period. i.e. they do not obey the rules of
PERF_RECORD_FINISHED_ROUND.
By adding an index, AUX area tracing events
can be found in advance and the
PERF_RECORD_FINISHED_ROUND approach works as
usual.
The index is recorded with the auxtrace feature
in the perf.data file. A session reads the index
but does not process it. An AUX area
decoder can queue all the AUX area data
in advance using auxtrace_queues__process_index()
or otherwise process the index in some custom
manner.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-inject.c | 15 +++
tools/perf/builtin-record.c | 15 +++
tools/perf/util/auxtrace.c | 216 ++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/auxtrace.h | 35 +++++++
| 31 ++++++-
tools/perf/util/session.c | 2 +
tools/perf/util/session.h | 1 +
7 files changed, 311 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index fc22249..cfb129a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -122,6 +122,18 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
tool);
int ret;
+ if (!inject->output.is_pipe) {
+ off_t offset;
+
+ offset = lseek(inject->output.fd, 0, SEEK_CUR);
+ if (offset == -1)
+ return -errno;
+ ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+ event, offset);
+ if (ret < 0)
+ return ret;
+ }
+
if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
ret = output_bytes(inject, event, event->header.size);
if (ret < 0)
@@ -487,6 +499,9 @@ static int __cmd_inject(struct perf_inject *inject)
output_data_offset = 4096;
}
+ if (!inject->itrace_synth_opts.set)
+ auxtrace_index__free(&session->auxtrace_index);
+
if (!file_out->is_pipe)
lseek(fd, output_data_offset, SEEK_SET);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 009ec31..8d6c2cb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -117,9 +117,24 @@ static int record__process_auxtrace(struct perf_tool *tool,
size_t len1, void *data2, size_t len2)
{
struct record *rec = container_of(tool, struct record, tool);
+ struct perf_data_file *file = &rec->file;
size_t padding;
u8 pad[8] = {0};
+ if (!perf_data_file__is_pipe(file)) {
+ off_t file_offset;
+ int fd = perf_data_file__fd(file);
+ int err;
+
+ file_offset = lseek(fd, 0, SEEK_CUR);
+ if (file_offset == -1)
+ return -1;
+ err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+ event, file_offset);
+ if (err)
+ return err;
+ }
+
/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
padding = (len1 + len2) & 7;
if (padding)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 434e394..02468b1 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -344,6 +344,33 @@ out_err:
return err;
}
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ off_t file_offset, size_t sz)
+{
+ union perf_event *event;
+ int err;
+ char buf[PERF_SAMPLE_MAX_SIZE];
+
+ err = perf_session__peek_event(session, file_offset, buf,
+ PERF_SAMPLE_MAX_SIZE, &event, NULL);
+ if (err)
+ return err;
+
+ if (event->header.type == PERF_RECORD_AUXTRACE) {
+ if (event->header.size != sizeof(struct auxtrace_event) ||
+ event->header.size != sz) {
+ err = -EINVAL;
+ goto out;
+ }
+ file_offset += event->header.size;
+ err = auxtrace_queues__add_event(queues, session, event,
+ file_offset, NULL);
+ }
+out:
+ return err;
+}
+
void auxtrace_queues__free(struct auxtrace_queues *queues)
{
unsigned int i;
@@ -500,6 +527,195 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
return NULL;
}
+static int auxtrace_index__alloc(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+
+ auxtrace_index = malloc(sizeof(struct auxtrace_index));
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ auxtrace_index->nr = 0;
+ INIT_LIST_HEAD(&auxtrace_index->list);
+
+ list_add_tail(&auxtrace_index->list, head);
+
+ return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index, *n;
+
+ list_for_each_entry_safe(auxtrace_index, n, head, list) {
+ list_del(&auxtrace_index->list);
+ free(auxtrace_index);
+ }
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ int err;
+
+ if (list_empty(head)) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ }
+
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+ if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+ list);
+ }
+
+ return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+ union perf_event *event, off_t file_offset)
+{
+ struct auxtrace_index *auxtrace_index;
+ size_t nr;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ nr = auxtrace_index->nr;
+ auxtrace_index->entries[nr].file_offset = file_offset;
+ auxtrace_index->entries[nr].sz = event->header.size;
+ auxtrace_index->nr += 1;
+
+ return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+ struct auxtrace_index *auxtrace_index)
+{
+ struct auxtrace_index_entry index;
+ size_t i;
+
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ index.file_offset = auxtrace_index->entries[i].file_offset;
+ index.sz = auxtrace_index->entries[i].sz;
+ if (writen(fd, &index, sizeof(index)) != sizeof(index))
+ return -errno;
+ }
+ return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ u64 total = 0;
+ int err;
+
+ list_for_each_entry(auxtrace_index, head, list)
+ total += auxtrace_index->nr;
+
+ if (writen(fd, &total, sizeof(total)) != sizeof(total))
+ return -errno;
+
+ list_for_each_entry(auxtrace_index, head, list) {
+ err = auxtrace_index__do_write(fd, auxtrace_index);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+ bool needs_swap)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry index;
+ size_t nr;
+
+ if (readn(fd, &index, sizeof(index)) != sizeof(index))
+ return -1;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -1;
+
+ nr = auxtrace_index->nr;
+ if (needs_swap) {
+ auxtrace_index->entries[nr].file_offset =
+ bswap_64(index.file_offset);
+ auxtrace_index->entries[nr].sz = bswap_64(index.sz);
+ } else {
+ auxtrace_index->entries[nr].file_offset = index.file_offset;
+ auxtrace_index->entries[nr].sz = index.sz;
+ }
+
+ auxtrace_index->nr = nr + 1;
+
+ return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap)
+{
+ struct list_head *head = &session->auxtrace_index;
+ u64 nr;
+
+ if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+ return -1;
+
+ if (needs_swap)
+ nr = bswap_64(nr);
+
+ if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) != size)
+ return -1;
+
+ while (nr--) {
+ int err;
+
+ err = auxtrace_index__process_entry(fd, head, needs_swap);
+ if (err)
+ return -1;
+ }
+
+ return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ struct auxtrace_index_entry *index)
+{
+ return auxtrace_queues__add_indexed_event(queues, session,
+ index->file_offset,
+ index->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry *index;
+ size_t i;
+ int err;
+
+ list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ index = &auxtrace_index->entries[i];
+ err = auxtrace_queues__process_index_entry(queues,
+ session,
+ index);
+ if (err)
+ return err;
+ }
+ }
+ return 0;
+}
+
struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
struct auxtrace_buffer *buffer)
{
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 53b60a6..b9e4b9d 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -80,6 +80,32 @@ struct itrace_synth_opts {
};
/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ * perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+ u64 file_offset;
+ u64 sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ * file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+ struct list_head list;
+ size_t nr;
+ struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
* struct auxtrace - session callbacks to allow AUX area data decoding.
* @process_event: lets the decoder see all session events
* @flush_events: process any remaining data
@@ -321,6 +347,8 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
union perf_event *event, off_t data_offset,
struct auxtrace_buffer **buffer_ptr);
void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session);
struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
struct auxtrace_buffer *buffer);
void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
@@ -361,6 +389,13 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
void auxtrace_record__free(struct auxtrace_record *itr);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+ off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
int code, int cpu, pid_t pid, pid_t tid, u64 ip,
const char *msg);
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a93c466..a1f4316 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,11 +869,18 @@ static int write_branch_stack(int fd __maybe_unused,
return 0;
}
-static int write_auxtrace(int fd __maybe_unused,
- struct perf_header *h __maybe_unused,
+static int write_auxtrace(int fd, struct perf_header *h,
struct perf_evlist *evlist __maybe_unused)
{
- return 0;
+ struct perf_session *session;
+ int err;
+
+ session = container_of(h, struct perf_session, header);
+
+ err = auxtrace_index__write(fd, &session->auxtrace_index);
+ if (err < 0)
+ pr_err("Failed to write auxtrace index\n");
+ return err;
}
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
@@ -1834,6 +1841,22 @@ out_free:
return ret;
}
+static int process_auxtrace(struct perf_file_section *section,
+ struct perf_header *ph, int fd,
+ void *data __maybe_unused)
+{
+ struct perf_session *session;
+ int err;
+
+ session = container_of(ph, struct perf_session, header);
+
+ err = auxtrace_index__process(fd, section->size, session,
+ ph->needs_swap);
+ if (err < 0)
+ pr_err("Failed to process auxtrace index\n");
+ return err;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1874,7 +1897,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
- FEAT_OPA(HEADER_AUXTRACE, auxtrace),
+ FEAT_OPP(HEADER_AUXTRACE, auxtrace),
};
struct header_print_data {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b08bf15..93833d0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -120,6 +120,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
session->repipe = repipe;
session->tool = tool;
+ INIT_LIST_HEAD(&session->auxtrace_index);
machines__init(&session->machines);
ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
@@ -187,6 +188,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
void perf_session__delete(struct perf_session *session)
{
auxtrace__free(session);
+ auxtrace_index__free(&session->auxtrace_index);
perf_session__destroy_kernel_maps(session);
perf_session__delete_threads(session);
perf_session_env__delete(&session->header.env);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9ed5135..b44afc7 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -24,6 +24,7 @@ struct perf_session {
struct perf_evlist *evlist;
struct auxtrace *auxtrace;
struct itrace_synth_opts *itrace_synth_opts;
+ struct list_head auxtrace_index;
struct trace_event tevent;
bool repipe;
bool one_mmap;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 22/44] perf tools: Hit all build ids when AUX area tracing
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (20 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 21/44] perf tools: Add AUX area tracing index Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 23/44] perf tools: Add build option NO_AUXTRACE to exclude " Adrian Hunter
` (21 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
We need to include all buildids when a perf.data
file contains AUX area tracing data because we
do not decode the trace for that purpose because
it would take too long.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-buildid-list.c | 9 +++++++++
tools/perf/builtin-inject.c | 8 +++++++-
tools/perf/builtin-record.c | 10 +++++++++-
3 files changed, 25 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index feb420f..9fe93c8 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -69,6 +69,15 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
+
+ /*
+ * We take all buildids when the file contains AUX area tracing data
+ * because we do not decode the trace because it would take too long.
+ */
+ if (!perf_data_file__is_pipe(&file) &&
+ perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ with_hits = false;
+
/*
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index cfb129a..aaf9b07 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -27,6 +27,7 @@ struct perf_inject {
struct perf_session *session;
bool build_ids;
bool sched_stat;
+ bool have_auxtrace;
const char *input_name;
struct perf_data_file output;
u64 bytes_written;
@@ -122,6 +123,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
tool);
int ret;
+ inject->have_auxtrace = true;
+
if (!inject->output.is_pipe) {
off_t offset;
@@ -508,9 +511,12 @@ static int __cmd_inject(struct perf_inject *inject)
ret = perf_session__process_events(session);
if (!file_out->is_pipe) {
- if (inject->build_ids)
+ if (inject->build_ids) {
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
+ if (inject->have_auxtrace)
+ dsos__hit_all(session);
+ }
/*
* The AUX areas have been removed and replaced with
* synthesized hardware events, so clear the feature flag.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8d6c2cb..3049b38 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -620,8 +620,16 @@ out_child:
if (!err && !file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
- if (!rec->no_buildid)
+ if (!rec->no_buildid) {
process_buildids(rec);
+ /*
+ * We take all buildids when the file contains
+ * AUX area tracing data because we do not decode the
+ * trace because it would take too long.
+ */
+ if (rec->opts.full_auxtrace)
+ dsos__hit_all(rec->session);
+ }
perf_session__write_header(rec->session, rec->evlist, fd, true);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 23/44] perf tools: Add build option NO_AUXTRACE to exclude AUX area tracing
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (21 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 22/44] perf tools: Hit all build ids when AUX area tracing Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-21 9:21 ` [PATCH V2 " Adrian Hunter
2015-04-09 15:54 ` [PATCH 24/44] perf auxtrace: Add option to synthesize events for transactions Adrian Hunter
` (20 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add build option NO_AUXTRACE to exclude compiling support
for AUX area tracing. Support for both recording and
processing is excluded and by implication any future
additions such as Intel PT and Intel BTS will also not
be compiled in with this option.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Makefile.perf | 2 +
tools/perf/builtin-inject.c | 53 +++++++++++-------
tools/perf/builtin-record.c | 13 +++++
tools/perf/config/Makefile | 5 ++
tools/perf/tests/make | 2 +
tools/perf/util/Build | 2 +-
tools/perf/util/auxtrace.h | 128 ++++++++++++++++++++++++++++++++++++++++++++
7 files changed, 185 insertions(+), 20 deletions(-)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a205..03409cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -73,6 +73,8 @@ include config/utilities.mak
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
ifeq ($(srctree),)
srctree := $(patsubst %/,%,$(dir $(shell pwd)))
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index aaf9b07..0dafe07 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -53,25 +53,6 @@ static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
return 0;
}
-static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
-{
- char buf[4096];
- ssize_t ssz;
- int ret;
-
- while (size > 0) {
- ssz = read(fd, buf, MIN(size, sizeof(buf)));
- if (ssz < 0)
- return -errno;
- ret = output_bytes(inject, buf, ssz);
- if (ret)
- return ret;
- size -= ssz;
- }
-
- return 0;
-}
-
static int perf_event__repipe_synth(struct perf_tool *tool,
union perf_event *event)
{
@@ -114,6 +95,27 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
return perf_event__repipe_synth(tool, event);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, MIN(size, sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session
@@ -153,6 +155,19 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
return event->auxtrace.size;
}
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+#endif
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3049b38..e3315d8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -112,6 +112,8 @@ out:
return rc;
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
static int record__process_auxtrace(struct perf_tool *tool,
union perf_event *event, void *data1,
size_t len1, void *data2, size_t len2)
@@ -165,6 +167,17 @@ static int record__auxtrace_mmap_read(struct record *rec,
return 0;
}
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+ struct auxtrace_mmap *mm __maybe_unused)
+{
+ return 0;
+}
+
+#endif
+
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 59a98c6..435b6ca 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -610,6 +610,11 @@ ifdef LIBBABELTRACE
endif
endif
+ifndef NO_AUXTRACE
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index bff8532..363fcd7 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -32,6 +32,7 @@ make_no_backtrace := NO_BACKTRACE=1
make_no_libnuma := NO_LIBNUMA=1
make_no_libaudit := NO_LIBAUDIT=1
make_no_libbionic := NO_LIBBIONIC=1
+make_no_auxtrace := NO_AUXTRACE=1
make_tags := tags
make_cscope := cscope
make_help := help
@@ -74,6 +75,7 @@ run += make_no_backtrace
run += make_no_libnuma
run += make_no_libaudit
run += make_no_libbionic
+run += make_no_auxtrace
run += make_help
run += make_doc
run += make_perf_o
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index b6c3f39..c8e3590 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -74,7 +74,7 @@ libperf-y += data.o
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
-libperf-y += auxtrace.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b9e4b9d..77b4699 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -26,6 +26,7 @@
#include "../perf.h"
#include "event.h"
#include "session.h"
+#include "debug.h"
union perf_event;
struct perf_session;
@@ -290,6 +291,8 @@ struct auxtrace_record {
int (*read_finish)(struct auxtrace_record *itr, int idx);
};
+#ifdef HAVE_AUXTRACE_SUPPORT
+
static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->userpg;
@@ -458,4 +461,129 @@ static inline void auxtrace__free(struct perf_session *session)
return session->auxtrace->free(session);
}
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err __maybe_unused)
+{
+ *err = 0;
+ return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+ struct perf_tool *tool __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ perf_event__handler_t process __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ struct record_opts *opts __maybe_unused)
+{
+ return 0;
+}
+
+#define perf_event__process_auxtrace_info 0
+#define perf_event__process_auxtrace 0
+#define perf_event__process_auxtrace_error 0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+ __maybe_unused,
+ union perf_event *event
+ __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+ __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_sample *sample __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+ struct list_head *head __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+ u64 size __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ bool needs_swap __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH V2 23/44] perf tools: Add build option NO_AUXTRACE to exclude AUX area tracing
2015-04-09 15:54 ` [PATCH 23/44] perf tools: Add build option NO_AUXTRACE to exclude " Adrian Hunter
@ 2015-04-21 9:21 ` Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-21 9:21 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add build option NO_AUXTRACE to exclude compiling support
for AUX area tracing. Support for both recording and
processing is excluded and by implication any future
additions such as Intel PT and Intel BTS will also not
be compiled in with this option.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
Changes in V2:
Get rid of MIN()
tools/perf/Makefile.perf | 2 +
tools/perf/builtin-inject.c | 53 +++++++++++-------
tools/perf/builtin-record.c | 13 +++++
tools/perf/config/Makefile | 5 ++
tools/perf/tests/make | 2 +
tools/perf/util/Build | 2 +-
tools/perf/util/auxtrace.h | 128 ++++++++++++++++++++++++++++++++++++++++++++
7 files changed, 185 insertions(+), 20 deletions(-)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a205..03409cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -73,6 +73,8 @@ include config/utilities.mak
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
ifeq ($(srctree),)
srctree := $(patsubst %/,%,$(dir $(shell pwd)))
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 79aabd1..cafc44b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -53,25 +53,6 @@ static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
return 0;
}
-static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
-{
- char buf[4096];
- ssize_t ssz;
- int ret;
-
- while (size > 0) {
- ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
- if (ssz < 0)
- return -errno;
- ret = output_bytes(inject, buf, ssz);
- if (ret)
- return ret;
- size -= ssz;
- }
-
- return 0;
-}
-
static int perf_event__repipe_synth(struct perf_tool *tool,
union perf_event *event)
{
@@ -114,6 +95,27 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
return perf_event__repipe_synth(tool, event);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session
@@ -153,6 +155,19 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
return event->auxtrace.size;
}
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+#endif
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4d0ebbb..dbb2c02 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -112,6 +112,8 @@ out:
return rc;
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
static int record__process_auxtrace(struct perf_tool *tool,
union perf_event *event, void *data1,
size_t len1, void *data2, size_t len2)
@@ -165,6 +167,17 @@ static int record__auxtrace_mmap_read(struct record *rec,
return 0;
}
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+ struct auxtrace_mmap *mm __maybe_unused)
+{
+ return 0;
+}
+
+#endif
+
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 59a98c6..435b6ca 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -610,6 +610,11 @@ ifdef LIBBABELTRACE
endif
endif
+ifndef NO_AUXTRACE
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 901ec91..af26410 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -32,6 +32,7 @@ make_no_backtrace := NO_BACKTRACE=1
make_no_libnuma := NO_LIBNUMA=1
make_no_libaudit := NO_LIBAUDIT=1
make_no_libbionic := NO_LIBBIONIC=1
+make_no_auxtrace := NO_AUXTRACE=1
make_tags := tags
make_cscope := cscope
make_help := help
@@ -74,6 +75,7 @@ run += make_no_backtrace
run += make_no_libnuma
run += make_no_libaudit
run += make_no_libbionic
+run += make_no_auxtrace
run += make_help
run += make_doc
run += make_perf_o
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index b6c3f39..c8e3590 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -74,7 +74,7 @@ libperf-y += data.o
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
-libperf-y += auxtrace.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b9e4b9d..77b4699 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -26,6 +26,7 @@
#include "../perf.h"
#include "event.h"
#include "session.h"
+#include "debug.h"
union perf_event;
struct perf_session;
@@ -290,6 +291,8 @@ struct auxtrace_record {
int (*read_finish)(struct auxtrace_record *itr, int idx);
};
+#ifdef HAVE_AUXTRACE_SUPPORT
+
static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->userpg;
@@ -458,4 +461,129 @@ static inline void auxtrace__free(struct perf_session *session)
return session->auxtrace->free(session);
}
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err __maybe_unused)
+{
+ *err = 0;
+ return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+ struct perf_tool *tool __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ perf_event__handler_t process __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ struct record_opts *opts __maybe_unused)
+{
+ return 0;
+}
+
+#define perf_event__process_auxtrace_info 0
+#define perf_event__process_auxtrace 0
+#define perf_event__process_auxtrace_error 0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+ __maybe_unused,
+ union perf_event *event
+ __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+ __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_sample *sample __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+ struct list_head *head __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+ u64 size __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ bool needs_swap __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 24/44] perf auxtrace: Add option to synthesize events for transactions
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (22 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 23/44] perf tools: Add build option NO_AUXTRACE to exclude " Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 25/44] perf script: Add field option 'flags' to print sample flags Adrian Hunter
` (19 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add AUX area tracing option 'x' to synthesize events for
transactions. This will be used by Intel PT to synthesize
an event record for each TSX start, commit or abort.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-report.txt | 9 +++++----
tools/perf/Documentation/perf-script.txt | 9 +++++----
tools/perf/util/auxtrace.c | 5 ++++-
tools/perf/util/auxtrace.h | 2 ++
4 files changed, 16 insertions(+), 9 deletions(-)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 66e3df3..f626fb2 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -331,11 +331,12 @@ OPTIONS
b synthesize branches events
c synthesize branches events (calls only)
r synthesize branches events (returns only)
+ x synthesize transactions events
e synthesize error events
d create a debug log
- g synthesize a call chain for instructions events
+ g synthesize a call chain (use with i or x)
- The default is all events i.e. the same as -Zibe
+ The default is all events i.e. the same as -Zibxe
In addition, the period (default 100000) for instructions events
can be specified in units of:
@@ -346,8 +347,8 @@ OPTIONS
us microseconds
ns nanoseconds (default)
- Also the call chain size (default 16, max. 1024) for instructions
- events can be specified.
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
To disable decoding entirely, use --no-itrace.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 0befc9c..8ea300d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -229,11 +229,12 @@ OPTIONS
b synthesize branches events
c synthesize branches events (calls only)
r synthesize branches events (returns only)
+ x synthesize transactions events
e synthesize error events
d create a debug log
- g synthesize a call chain for instructions events
+ g synthesize a call chain (use with i or x)
- The default is all events i.e. the same as -Zibe
+ The default is all events i.e. the same as -Zibxe
In addition, the period (default 100000) for instructions events
can be specified in units of:
@@ -244,8 +245,8 @@ OPTIONS
us microseconds
ns nanoseconds (default)
- Also the call chain size (default 16, max. 1024) for instructions
- events can be specified.
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
To disable decoding entirely, use --no-itrace.
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 02468b1..b591a9b 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -889,6 +889,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
{
synth_opts->instructions = true;
synth_opts->branches = true;
+ synth_opts->transactions = true;
synth_opts->errors = true;
synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
@@ -956,6 +957,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
case 'b':
synth_opts->branches = true;
break;
+ case 'x':
+ synth_opts->transactions = true;
+ break;
case 'e':
synth_opts->errors = true;
break;
@@ -971,7 +975,6 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
synth_opts->returns = true;
break;
case 'g':
- synth_opts->instructions = true;
synth_opts->callchain = true;
synth_opts->callchain_sz =
PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 77b4699..8c6cbb1 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -54,6 +54,7 @@ enum itrace_period_type {
* because 'perf inject' will write it out
* @instructions: whether to synthesize 'instructions' events
* @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
* @errors: whether to synthesize decoder error events
* @dont_decode: whether to skip decoding entirely
* @log: write a decoding log
@@ -69,6 +70,7 @@ struct itrace_synth_opts {
bool inject;
bool instructions;
bool branches;
+ bool transactions;
bool errors;
bool dont_decode;
bool log;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 25/44] perf script: Add field option 'flags' to print sample flags
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (23 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 24/44] perf auxtrace: Add option to synthesize events for transactions Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-05-06 3:03 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:54 ` [PATCH 26/44] perf tools: Add aux_watermark member of struct perf_event_attr Adrian Hunter
` (18 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Instruction tracing will typically have access to information
about the instruction being executed for a particular ip sample.
Some of that information will be available in the 'flags' member
of struct perf_sample.
With the addition of transactions events synthesis to Instruction
Tracing options, there is a need to be able easily to see the
flags because they show whether the ip is at the start, commit or
abort of a tranasaction.
Consequently add an option to display the flags.
The flags are "bcrosyiABEx" which stand for branch, call, return,
conditional, system, asynchronous, interrupt, transaction abort,
trace begin, trace end, and in transaction, respectively.
Example using Intel PT:
perf script -fip,time,event,sym,addr,flags
...
1288.721584105: branches:u: bo 401146 main => 401152 main
1288.721584105: transactions: x 0 401164 main
1288.721584105: branches:u: bx 40117c main => 40119b main
1288.721584105: branches:u: box 4011a4 main => 40117e main
1288.721584105: branches:u: bcx 401187 main => 401094 g
...
1288.721591645: branches:u: bx 4010c4 g => 4010cb g
1288.721591645: branches:u: brx 4010cc g => 401189 main
1288.721591645: transactions: 0 4011a6 main
1288.721593199: branches:u: b 4011a9 main => 4011af main
1288.721593199: branches:u: bo 4011bc main => 40113e main
1288.721593199: branches:u: b 401150 main => 40115a main
1288.721593199: transactions: x 0 401164 main
1288.721593199: branches:u: bx 40117c main => 40119b main
1288.721593199: branches:u: box 4011a4 main => 40117e main
1288.721593199: branches:u: bcx 401187 main => 40105e f
...
1288.722284747: branches:u: brx 401093 f => 401189 main
1288.722284747: branches:u: box 4011a4 main => 40117e main
1288.722284747: branches:u: bcx 401187 main => 40105e f
1288.722285883: transactions: bA 0 401071 f
1288.722285883: branches:u: bA 401071 f => 40116a main
1288.722285883: branches:u: bE 40116a main => 0 [unknown]
1288.722297174: branches:u: bB 0 [unknown] => 40116a main
...
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-script.txt | 9 ++++++++-
tools/perf/builtin-script.c | 34 +++++++++++++++++++++++++++-----
tools/perf/util/event.h | 2 ++
3 files changed, 39 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 8ea300d..576f9d4 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,8 @@ OPTIONS
-f::
--fields::
Comma separated list of fields to print. Options are:
- comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+ comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+ srcline, period, flags.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
@@ -165,6 +166,12 @@ OPTIONS
At this point usage is displayed, and perf-script exits.
+ The flags field is synthesized and may have a value when Instruction
+ Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+ call, return, conditional, system, asynchronous, interrupt,
+ transaction abort, trace begin, trace end, and in transaction,
+ respectively.
+
Finally, a user may not set fields to none for all event types.
i.e., -f "" is not allowed.
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7346045..15cf5df 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -27,6 +27,7 @@ static u64 nr_unordered;
static bool no_callchain;
static bool latency_format;
static bool system_wide;
+static bool print_flags;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -461,6 +462,25 @@ static void print_sample_bts(union perf_event *event,
printf("\n");
}
+static void print_sample_flags(u32 flags)
+{
+ const char *chars = PERF_IP_FLAG_CHARS;
+ const int n = strlen(PERF_IP_FLAG_CHARS);
+ char str[33];
+ int i, pos = 0;
+
+ for (i = 0; i < n; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = chars[i];
+ }
+ for (; i < 32; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = '?';
+ }
+ str[pos] = 0;
+ printf(" %-4s ", str);
+}
+
static void process_event(union perf_event *event, struct perf_sample *sample,
struct perf_evsel *evsel, struct addr_location *al)
{
@@ -480,6 +500,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
printf("%s: ", evname ? evname : "[unknown]");
}
+ if (print_flags)
+ print_sample_flags(sample->flags);
+
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, thread, al);
return;
@@ -1015,12 +1038,15 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
}
}
- tok = strtok(tok, ",");
- while (tok) {
+ for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
for (i = 0; i < imax; ++i) {
if (strcmp(tok, all_output_options[i].str) == 0)
break;
}
+ if (i == imax && strcmp(tok, "flags") == 0) {
+ print_flags = true;
+ continue;
+ }
if (i == imax) {
fprintf(stderr, "Invalid field requested.\n");
rc = -EINVAL;
@@ -1048,8 +1074,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
}
output[type].fields |= all_output_options[i].field;
}
-
- tok = strtok(NULL, ",");
}
if (type >= 0) {
@@ -1570,7 +1594,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"comma separated output fields prepend with 'type:'. "
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period", parse_output_fields),
+ "addr,symoff,period,flags", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8ef3725..80e9f59 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -157,6 +157,8 @@ enum {
PERF_IP_FLAG_IN_TX = 1ULL << 10,
};
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
#define PERF_BRANCH_MASK (\
PERF_IP_FLAG_BRANCH |\
PERF_IP_FLAG_CALL |\
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf script: Add field option 'flags' to print sample flags
2015-04-09 15:54 ` [PATCH 25/44] perf script: Add field option 'flags' to print sample flags Adrian Hunter
@ 2015-05-06 3:03 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:03 UTC (permalink / raw)
To: linux-tip-commits
Cc: linux-kernel, adrian.hunter, tglx, jolsa, dsahern, mingo, hpa,
eranian, acme, peterz, fweisbec, namhyung
Commit-ID: 400ea6d327ff43311c73dd4a000eb064ae20140c
Gitweb: http://git.kernel.org/tip/400ea6d327ff43311c73dd4a000eb064ae20140c
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:54:05 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:57 -0300
perf script: Add field option 'flags' to print sample flags
Instruction tracing will typically have access to information about the
instruction being executed for a particular ip sample. Some of that
information will be available in the 'flags' member of struct
perf_sample.
With the addition of transactions events synthesis to Instruction
Tracing options, there is a need to be able easily to see the flags
because they show whether the ip is at the start, commit or abort of a
tranasaction.
Consequently add an option to display the flags.
The flags are "bcrosyiABEx" which stand for branch, call, return,
conditional, system, asynchronous, interrupt, transaction abort, trace
begin, trace end, and in transaction, respectively.
Example using Intel PT:
perf script -fip,time,event,sym,addr,flags
...
1288.721584105: branches:u: bo 401146 main => 401152 main
1288.721584105: transactions: x 0 401164 main
1288.721584105: branches:u: bx 40117c main => 40119b main
1288.721584105: branches:u: box 4011a4 main => 40117e main
1288.721584105: branches:u: bcx 401187 main => 401094 g
...
1288.721591645: branches:u: bx 4010c4 g => 4010cb g
1288.721591645: branches:u: brx 4010cc g => 401189 main
1288.721591645: transactions: 0 4011a6 main
1288.721593199: branches:u: b 4011a9 main => 4011af main
1288.721593199: branches:u: bo 4011bc main => 40113e main
1288.721593199: branches:u: b 401150 main => 40115a main
1288.721593199: transactions: x 0 401164 main
1288.721593199: branches:u: bx 40117c main => 40119b main
1288.721593199: branches:u: box 4011a4 main => 40117e main
1288.721593199: branches:u: bcx 401187 main => 40105e f
...
1288.722284747: branches:u: brx 401093 f => 401189 main
1288.722284747: branches:u: box 4011a4 main => 40117e main
1288.722284747: branches:u: bcx 401187 main => 40105e f
1288.722285883: transactions: bA 0 401071 f
1288.722285883: branches:u: bA 401071 f => 40116a main
1288.722285883: branches:u: bE 40116a main => 0 [unknown]
1288.722297174: branches:u: bB 0 [unknown] => 40116a main
...
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-26-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-script.txt | 9 ++++++++-
tools/perf/builtin-script.c | 34 +++++++++++++++++++++++++++-----
tools/perf/util/event.h | 2 ++
3 files changed, 39 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 05df648..b29cd2f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,8 @@ OPTIONS
-f::
--fields::
Comma separated list of fields to print. Options are:
- comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+ comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+ srcline, period, flags.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
@@ -165,6 +166,12 @@ OPTIONS
At this point usage is displayed, and perf-script exits.
+ The flags field is synthesized and may have a value when Instruction
+ Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+ call, return, conditional, system, asynchronous, interrupt,
+ transaction abort, trace begin, trace end, and in transaction,
+ respectively.
+
Finally, a user may not set fields to none for all event types.
i.e., -f "" is not allowed.
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7682665..cd2f38b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -27,6 +27,7 @@ static u64 nr_unordered;
static bool no_callchain;
static bool latency_format;
static bool system_wide;
+static bool print_flags;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -446,6 +447,25 @@ static void print_sample_bts(union perf_event *event,
printf("\n");
}
+static void print_sample_flags(u32 flags)
+{
+ const char *chars = PERF_IP_FLAG_CHARS;
+ const int n = strlen(PERF_IP_FLAG_CHARS);
+ char str[33];
+ int i, pos = 0;
+
+ for (i = 0; i < n; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = chars[i];
+ }
+ for (; i < 32; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = '?';
+ }
+ str[pos] = 0;
+ printf(" %-4s ", str);
+}
+
static void process_event(union perf_event *event, struct perf_sample *sample,
struct perf_evsel *evsel, struct addr_location *al)
{
@@ -465,6 +485,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
printf("%s: ", evname ? evname : "[unknown]");
}
+ if (print_flags)
+ print_sample_flags(sample->flags);
+
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, thread, al);
return;
@@ -1000,12 +1023,15 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
}
}
- tok = strtok(tok, ",");
- while (tok) {
+ for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
for (i = 0; i < imax; ++i) {
if (strcmp(tok, all_output_options[i].str) == 0)
break;
}
+ if (i == imax && strcmp(tok, "flags") == 0) {
+ print_flags = true;
+ continue;
+ }
if (i == imax) {
fprintf(stderr, "Invalid field requested.\n");
rc = -EINVAL;
@@ -1033,8 +1059,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
}
output[type].fields |= all_output_options[i].field;
}
-
- tok = strtok(NULL, ",");
}
if (type >= 0) {
@@ -1555,7 +1579,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"comma separated output fields prepend with 'type:'. "
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period", parse_output_fields),
+ "addr,symoff,period,flags", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8ef3725..80e9f59 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -157,6 +157,8 @@ enum {
PERF_IP_FLAG_IN_TX = 1ULL << 10,
};
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
#define PERF_BRANCH_MASK (\
PERF_IP_FLAG_BRANCH |\
PERF_IP_FLAG_CALL |\
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 26/44] perf tools: Add aux_watermark member of struct perf_event_attr
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (24 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 25/44] perf script: Add field option 'flags' to print sample flags Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-05-06 3:03 ` [tip:perf/core] " tip-bot for Adrian Hunter
2015-04-09 15:54 ` [PATCH 27/44] perf tools: Add support for PERF_RECORD_AUX Adrian Hunter
` (17 subsequent siblings)
43 siblings, 1 reply; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add new AUX area member (aux_watermark) of struct perf_event_attr
to debug prints and byte swapping.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/evsel.c | 1 +
tools/perf/util/session.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8..c886b9f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1121,6 +1121,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
+ PRINT_ATTRf(aux_watermark, p_unsigned);
return ret;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 93833d0..70c35f9 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -502,6 +502,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
attr->branch_sample_type = bswap_64(attr->branch_sample_type);
attr->sample_regs_user = bswap_64(attr->sample_regs_user);
attr->sample_stack_user = bswap_32(attr->sample_stack_user);
+ attr->aux_watermark = bswap_32(attr->aux_watermark);
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [tip:perf/core] perf tools: Add aux_watermark member of struct perf_event_attr
2015-04-09 15:54 ` [PATCH 26/44] perf tools: Add aux_watermark member of struct perf_event_attr Adrian Hunter
@ 2015-05-06 3:03 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 79+ messages in thread
From: tip-bot for Adrian Hunter @ 2015-05-06 3:03 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, acme, peterz, namhyung, adrian.hunter, mingo, hpa, tglx,
linux-kernel, jolsa, fweisbec, dsahern
Commit-ID: 70d73de4cd571df09670e2a7bf36a912e9ff5138
Gitweb: http://git.kernel.org/tip/70d73de4cd571df09670e2a7bf36a912e9ff5138
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 9 Apr 2015 18:54:06 +0300
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 29 Apr 2015 10:37:58 -0300
perf tools: Add aux_watermark member of struct perf_event_attr
Add new AUX area member (aux_watermark) of struct perf_event_attr to
debug prints and byte swapping.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1428594864-29309-27-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evsel.c | 1 +
tools/perf/util/session.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8..c886b9f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1121,6 +1121,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
+ PRINT_ATTRf(aux_watermark, p_unsigned);
return ret;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1db3ce1..90fa567 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -500,6 +500,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
attr->branch_sample_type = bswap_64(attr->branch_sample_type);
attr->sample_regs_user = bswap_64(attr->sample_regs_user);
attr->sample_stack_user = bswap_32(attr->sample_stack_user);
+ attr->aux_watermark = bswap_32(attr->aux_watermark);
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
^ permalink raw reply related [flat|nested] 79+ messages in thread
* [PATCH 27/44] perf tools: Add support for PERF_RECORD_AUX
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (25 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 26/44] perf tools: Add aux_watermark member of struct perf_event_attr Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 28/44] perf tools: Add support for PERF_RECORD_ITRACE_START Adrian Hunter
` (16 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for the PERF_RECORD_AUX event type.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-inject.c | 1 +
tools/perf/util/event.c | 21 +++++++++++++++++++++
tools/perf/util/event.h | 13 +++++++++++++
tools/perf/util/machine.c | 10 ++++++++++
tools/perf/util/machine.h | 2 ++
tools/perf/util/session.c | 15 +++++++++++++++
tools/perf/util/tool.h | 1 +
7 files changed, 63 insertions(+)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0dafe07..66492be 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -558,6 +558,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.fork = perf_event__repipe,
.exit = perf_event__repipe,
.lost = perf_event__repipe,
+ .aux = perf_event__repipe,
.read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index a0c8740..2f63449 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -23,6 +23,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
+ [PERF_RECORD_AUX] = "AUX",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -684,6 +685,14 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
return machine__process_lost_event(machine, event, sample);
}
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_aux_event(machine, event);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -747,6 +756,15 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
return machine__process_exit_event(machine, event, sample);
}
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+ event->aux.aux_offset, event->aux.aux_size,
+ event->aux.flags,
+ event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+ event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -766,6 +784,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
case PERF_RECORD_MMAP2:
ret += perf_event__fprintf_mmap2(event, fp);
break;
+ case PERF_RECORD_AUX:
+ ret += perf_event__fprintf_aux(event, fp);
+ break;
default:
ret += fprintf(fp, "\n");
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 80e9f59..b3c350e 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -323,6 +323,13 @@ struct auxtrace_error_event {
char msg[MAX_AUXTRACE_ERROR_MSG];
};
+struct aux_event {
+ struct perf_event_header header;
+ u64 aux_offset;
+ u64 aux_size;
+ u64 flags;
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -341,6 +348,7 @@ union perf_event {
struct auxtrace_info_event auxtrace_info;
struct auxtrace_event auxtrace;
struct auxtrace_error_event auxtrace_error;
+ struct aux_event aux;
};
void perf_event__print_totals(void);
@@ -376,6 +384,10 @@ int perf_event__process_lost(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -433,6 +445,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9c380a2..25fc1b6 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -488,6 +488,14 @@ machine__module_dso(struct machine *machine, struct kmod_path *m,
return dso;
}
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_aux(event, stdout);
+ return 0;
+}
+
struct map *machine__new_module(struct machine *machine, u64 start,
const char *filename)
{
@@ -1333,6 +1341,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
ret = machine__process_exit_event(machine, event, sample); break;
case PERF_RECORD_LOST:
ret = machine__process_lost_event(machine, event, sample); break;
+ case PERF_RECORD_AUX:
+ ret = machine__process_aux_event(machine, event); break;
default:
ret = -1;
break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e2faf3b..97608ed 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -81,6 +81,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
struct perf_sample *sample);
int machine__process_lost_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+ union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 70c35f9..0fdeb1e1 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -325,6 +325,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->exit = process_event_stub;
if (tool->lost == NULL)
tool->lost = perf_event__process_lost;
+ if (tool->aux == NULL)
+ tool->aux = perf_event__process_aux;
if (tool->read == NULL)
tool->read = process_event_sample_stub;
if (tool->throttle == NULL)
@@ -443,6 +445,16 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
swap_sample_id_all(event, &event->read + 1);
}
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+ event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+ event->aux.aux_size = bswap_64(event->aux.aux_size);
+ event->aux.flags = bswap_64(event->aux.flags);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->aux + 1);
+}
+
static void perf_event__throttle_swap(union perf_event *event,
bool sample_id_all)
{
@@ -580,6 +592,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_THROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
+ [PERF_RECORD_AUX] = perf_event__aux_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1029,6 +1042,8 @@ static int machines__deliver_event(struct machines *machines,
return tool->throttle(tool, event, sample, machine);
case PERF_RECORD_UNTHROTTLE:
return tool->unthrottle(tool, event, sample, machine);
+ case PERF_RECORD_AUX:
+ return tool->aux(tool, event, sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 20afe19..8288caf 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -43,6 +43,7 @@ struct perf_tool {
fork,
exit,
lost,
+ aux,
throttle,
unthrottle;
event_attr_op attr;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 28/44] perf tools: Add support for PERF_RECORD_ITRACE_START
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (26 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 27/44] perf tools: Add support for PERF_RECORD_AUX Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 29/44] perf tools: Add AUX area tracing Snapshot Mode Adrian Hunter
` (15 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for the PERF_RECORD_ITRACE_START event type.
This event can be used to determine the pid and tid that
are running when Instruction Tracing starts. Generally
that information would come from a sched_switch event
but, at the start, no sched_switch events may yet have
been recorded.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/builtin-inject.c | 1 +
tools/perf/util/event.c | 18 ++++++++++++++++++
tools/perf/util/event.h | 11 +++++++++++
tools/perf/util/machine.c | 11 +++++++++++
tools/perf/util/machine.h | 2 ++
tools/perf/util/session.c | 15 +++++++++++++++
tools/perf/util/tool.h | 1 +
7 files changed, 59 insertions(+)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 66492be..56fa34e 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -559,6 +559,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.exit = perf_event__repipe,
.lost = perf_event__repipe,
.aux = perf_event__repipe,
+ .itrace_start = perf_event__repipe,
.read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2f63449..f03bc0d 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -24,6 +24,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_AUX] = "AUX",
+ [PERF_RECORD_ITRACE_START] = "ITRACE_START",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -693,6 +694,14 @@ int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
return machine__process_aux_event(machine, event);
}
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_itrace_start_event(machine, event);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -765,6 +774,12 @@ size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
}
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " pid: %u tid: %u\n",
+ event->itrace_start.pid, event->itrace_start.tid);
+}
+
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -787,6 +802,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
case PERF_RECORD_AUX:
ret += perf_event__fprintf_aux(event, fp);
break;
+ case PERF_RECORD_ITRACE_START:
+ ret += perf_event__fprintf_itrace_start(event, fp);
+ break;
default:
ret += fprintf(fp, "\n");
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b3c350e..7eecd5e 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -330,6 +330,11 @@ struct aux_event {
u64 flags;
};
+struct itrace_start_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -349,6 +354,7 @@ union perf_event {
struct auxtrace_event auxtrace;
struct auxtrace_error_event auxtrace_error;
struct aux_event aux;
+ struct itrace_start_event itrace_start;
};
void perf_event__print_totals(void);
@@ -388,6 +394,10 @@ int perf_event__process_aux(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -446,6 +456,7 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 25fc1b6..0aec99a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -496,6 +496,14 @@ int machine__process_aux_event(struct machine *machine __maybe_unused,
return 0;
}
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_itrace_start(event, stdout);
+ return 0;
+}
+
struct map *machine__new_module(struct machine *machine, u64 start,
const char *filename)
{
@@ -1343,6 +1351,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
ret = machine__process_lost_event(machine, event, sample); break;
case PERF_RECORD_AUX:
ret = machine__process_aux_event(machine, event); break;
+ case PERF_RECORD_ITRACE_START:
+ ret = machine__process_itrace_start_event(machine, event);
+ break;
default:
ret = -1;
break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 97608ed..10df678 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -83,6 +83,8 @@ int machine__process_lost_event(struct machine *machine, union perf_event *event
struct perf_sample *sample);
int machine__process_aux_event(struct machine *machine,
union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+ union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0fdeb1e1..71b4ec8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -327,6 +327,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->lost = perf_event__process_lost;
if (tool->aux == NULL)
tool->aux = perf_event__process_aux;
+ if (tool->itrace_start == NULL)
+ tool->itrace_start = perf_event__process_itrace_start;
if (tool->read == NULL)
tool->read = process_event_sample_stub;
if (tool->throttle == NULL)
@@ -455,6 +457,16 @@ static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
swap_sample_id_all(event, &event->aux + 1);
}
+static void perf_event__itrace_start_swap(union perf_event *event,
+ bool sample_id_all)
+{
+ event->itrace_start.pid = bswap_32(event->itrace_start.pid);
+ event->itrace_start.tid = bswap_32(event->itrace_start.tid);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
static void perf_event__throttle_swap(union perf_event *event,
bool sample_id_all)
{
@@ -593,6 +605,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
[PERF_RECORD_AUX] = perf_event__aux_swap,
+ [PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1044,6 +1057,8 @@ static int machines__deliver_event(struct machines *machines,
return tool->unthrottle(tool, event, sample, machine);
case PERF_RECORD_AUX:
return tool->aux(tool, event, sample, machine);
+ case PERF_RECORD_ITRACE_START:
+ return tool->itrace_start(tool, event, sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 8288caf..7f282ad 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -44,6 +44,7 @@ struct perf_tool {
exit,
lost,
aux,
+ itrace_start,
throttle,
unthrottle;
event_attr_op attr;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 29/44] perf tools: Add AUX area tracing Snapshot Mode
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (27 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 28/44] perf tools: Add support for PERF_RECORD_ITRACE_START Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 30/44] perf record: Add AUX area tracing Snapshot Mode support Adrian Hunter
` (14 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for making snapshots of
AUX area tracing data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/perf.h | 3 ++
tools/perf/util/auxtrace.c | 85 ++++++++++++++++++++++++++++++++++++++++------
tools/perf/util/auxtrace.h | 41 ++++++++++++++++++++++
3 files changed, 119 insertions(+), 10 deletions(-)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 5042093..aa79fb8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -55,6 +55,7 @@ struct record_opts {
bool sample_intr_regs;
bool running_time;
bool full_auxtrace;
+ bool auxtrace_snapshot_mode;
unsigned int freq;
unsigned int mmap_pages;
unsigned int auxtrace_mmap_pages;
@@ -62,6 +63,8 @@ struct record_opts {
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ size_t auxtrace_snapshot_size;
+ const char *auxtrace_snapshot_opts;
bool sample_transaction;
unsigned initial_delay;
bool use_clockid;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index b591a9b..4373f97 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -504,6 +504,29 @@ void auxtrace_record__free(struct auxtrace_record *itr)
itr->free(itr);
}
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_start)
+ return itr->snapshot_start(itr);
+ return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_finish)
+ return itr->snapshot_finish(itr);
+ return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old)
+{
+ if (itr && itr->find_snapshot)
+ return itr->find_snapshot(itr, idx, mm, data, head, old);
+ return 0;
+}
+
int auxtrace_record__options(struct auxtrace_record *itr,
struct perf_evlist *evlist,
struct record_opts *opts)
@@ -520,6 +543,19 @@ u64 auxtrace_record__reference(struct auxtrace_record *itr)
return 0;
}
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts, const char *str)
+{
+ if (!str)
+ return 0;
+
+ if (itr)
+ return itr->parse_snapshot_options(itr, opts, str);
+
+ pr_err("No AUX area tracing to snapshot\n");
+ return -EINVAL;
+}
+
struct auxtrace_record *__weak
auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
{
@@ -1073,16 +1109,26 @@ int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
return 0;
}
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
- struct perf_tool *tool, process_auxtrace_t fn)
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ bool snapshot, size_t snapshot_size)
{
- u64 head = auxtrace_mmap__read_head(mm);
- u64 old = mm->prev, offset, ref;
+ u64 head, old = mm->prev, offset, ref;
unsigned char *data = mm->base;
size_t size, head_off, old_off, len1, len2, padding;
union perf_event ev;
void *data1, *data2;
+ if (snapshot) {
+ head = auxtrace_mmap__read_snapshot_head(mm);
+ if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data, &head,
+ &old))
+ return -1;
+ } else {
+ head = auxtrace_mmap__read_head(mm);
+ }
+
if (old == head)
return 0;
@@ -1102,6 +1148,9 @@ int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
else
size = mm->len - (old_off - head_off);
+ if (snapshot && size > snapshot_size)
+ size = snapshot_size;
+
ref = auxtrace_record__reference(itr);
if (head > old || size <= head || mm->mask) {
@@ -1149,18 +1198,34 @@ int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
mm->prev = head;
- auxtrace_mmap__write_tail(mm, head);
- if (itr->read_finish) {
- int err;
+ if (!snapshot) {
+ auxtrace_mmap__write_tail(mm, head);
+ if (itr->read_finish) {
+ int err;
- err = itr->read_finish(itr, mm->idx);
- if (err < 0)
- return err;
+ err = itr->read_finish(itr, mm->idx);
+ if (err < 0)
+ return err;
+ }
}
return 1;
}
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+}
+
/**
* struct auxtrace_cache - hash table to implement a cache
* @hashtable: the hashtable
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 8c6cbb1..f0bacb6 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -276,6 +276,10 @@ struct auxtrace_mmap_params {
* @info_priv_size: return the size of the private data in auxtrace_info_event
* @info_fill: fill-in the private data in auxtrace_info_event
* @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
* @reference: provide a 64-bit reference number for auxtrace_event
* @read_finish: called after reading from an auxtrace mmap
*/
@@ -289,12 +293,36 @@ struct auxtrace_record {
struct auxtrace_info_event *auxtrace_info,
size_t priv_size);
void (*free)(struct auxtrace_record *itr);
+ int (*snapshot_start)(struct auxtrace_record *itr);
+ int (*snapshot_finish)(struct auxtrace_record *itr);
+ int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 *head, u64 *old);
+ int (*parse_snapshot_options)(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
u64 (*reference)(struct auxtrace_record *itr);
int (*read_finish)(struct auxtrace_record *itr, int idx);
};
#ifdef HAVE_AUXTRACE_SUPPORT
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic. However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+ u64 head = ACCESS_ONCE(pc->aux_head);
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->userpg;
@@ -346,6 +374,11 @@ typedef int (*process_auxtrace_t)(struct perf_tool *tool,
int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
struct perf_tool *tool, process_auxtrace_t fn);
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size);
+
int auxtrace_queues__init(struct auxtrace_queues *queues);
int auxtrace_queues__add_event(struct auxtrace_queues *queues,
struct perf_session *session,
@@ -383,6 +416,9 @@ void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
int *err);
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
int auxtrace_record__options(struct auxtrace_record *itr,
struct perf_evlist *evlist,
struct record_opts *opts);
@@ -392,6 +428,11 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
struct auxtrace_info_event *auxtrace_info,
size_t priv_size);
void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 30/44] perf record: Add AUX area tracing Snapshot Mode support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (28 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 29/44] perf tools: Add AUX area tracing Snapshot Mode Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 31/44] perf auxtrace: Add Intel PT as an AUX area tracing type Adrian Hunter
` (13 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add a new option and support for Instruction
Tracing Snapshot Mode. When the new option is
selected, no AUX area tracing data is
captured until a signal (SIGUSR2) is received.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/perf-record.txt | 7 ++
tools/perf/builtin-record.c | 144 ++++++++++++++++++++++++++-----
tools/perf/util/auxtrace.h | 11 +++
tools/perf/util/parse-options.h | 4 +
4 files changed, 145 insertions(+), 21 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 76a141e..57dd57b 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -259,6 +259,13 @@ records. See clock_gettime(). In particular CLOCK_MONOTONIC and
CLOCK_MONOTONIC_RAW are supported, some events might also allow
CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
+-S::
+--snapshot::
+Select AUX area tracing Snapshot Mode. This option is valid only with an
+AUX area tracing event. Optionally the number of bytes to capture per
+snapshot can be specified. In Snapshot Mode, trace data is captured only when
+signal SIGUSR2 is received.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e3315d8..7358fe1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -112,6 +112,32 @@ out:
return rc;
}
+static volatile int done = 0;
+static volatile int signr = -1;
+static volatile int child_finished = 0;
+static volatile int auxtrace_snapshot_enabled;
+static volatile int auxtrace_snapshot_err;
+static volatile int auxtrace_record__snapshot_started;
+
+static void sig_handler(int sig)
+{
+ if (sig == SIGCHLD)
+ child_finished = 1;
+ else
+ signr = sig;
+
+ done = 1;
+}
+
+static void record__sig_exit(void)
+{
+ if (signr == -1)
+ return;
+
+ signal(signr, SIG_DFL);
+ raise(signr);
+}
+
#ifdef HAVE_AUXTRACE_SUPPORT
static int record__process_auxtrace(struct perf_tool *tool,
@@ -167,6 +193,56 @@ static int record__auxtrace_mmap_read(struct record *rec,
return 0;
}
+static int record__auxtrace_mmap_read_snapshot(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+ record__process_auxtrace,
+ rec->opts.auxtrace_snapshot_size);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
+static int record__auxtrace_read_snapshot_all(struct record *rec)
+{
+ int i;
+ int rc = 0;
+
+ for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm =
+ &rec->evlist->mmap[i].auxtrace_mmap;
+
+ if (!mm->base)
+ continue;
+
+ if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
+ }
+out:
+ return rc;
+}
+
+static void record__read_auxtrace_snapshot(struct record *rec)
+{
+ pr_debug("Recording AUX area tracing snapshot\n");
+ if (record__auxtrace_read_snapshot_all(rec) < 0) {
+ auxtrace_snapshot_err = -1;
+ } else {
+ auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
+ if (!auxtrace_snapshot_err)
+ auxtrace_snapshot_enabled = 1;
+ }
+}
+
#else
static inline
@@ -176,31 +252,19 @@ int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
return 0;
}
-#endif
-
-static volatile int done = 0;
-static volatile int signr = -1;
-static volatile int child_finished = 0;
-
-static void sig_handler(int sig)
+static inline
+void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
{
- if (sig == SIGCHLD)
- child_finished = 1;
- else
- signr = sig;
-
- done = 1;
}
-static void record__sig_exit(void)
+static inline
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
{
- if (signr == -1)
- return;
-
- signal(signr, SIG_DFL);
- raise(signr);
+ return 0;
}
+#endif
+
static int record__open(struct record *rec)
{
char msg[512];
@@ -238,7 +302,8 @@ try_again:
}
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
- opts->auxtrace_mmap_pages, false) < 0) {
+ opts->auxtrace_mmap_pages,
+ opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -349,7 +414,7 @@ static int record__mmap_read_all(struct record *rec)
}
}
- if (mm->base &&
+ if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
record__auxtrace_mmap_read(rec, mm) != 0) {
rc = -1;
goto out;
@@ -404,6 +469,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
child_finished = 1;
}
+static void snapshot_sig_handler(int sig);
+
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
@@ -424,6 +491,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
+ if (rec->opts.auxtrace_snapshot_mode)
+ signal(SIGUSR2, snapshot_sig_handler);
+ else
+ signal(SIGUSR2, SIG_IGN);
session = perf_session__new(file, false, tool);
if (session == NULL) {
@@ -563,14 +634,27 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
perf_evlist__enable(rec->evlist);
}
+ auxtrace_snapshot_enabled = 1;
for (;;) {
int hits = rec->samples;
if (record__mmap_read_all(rec) < 0) {
+ auxtrace_snapshot_enabled = 0;
err = -1;
goto out_child;
}
+ if (auxtrace_record__snapshot_started) {
+ auxtrace_record__snapshot_started = 0;
+ if (!auxtrace_snapshot_err)
+ record__read_auxtrace_snapshot(rec);
+ if (auxtrace_snapshot_err) {
+ pr_err("AUX area tracing snapshot failed\n");
+ err = -1;
+ goto out_child;
+ }
+ }
+
if (hits == rec->samples) {
if (done || draining)
break;
@@ -593,10 +677,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
* disable events in this case.
*/
if (done && !disabled && !target__none(&opts->target)) {
+ auxtrace_snapshot_enabled = 0;
perf_evlist__disable(rec->evlist);
disabled = true;
}
}
+ auxtrace_snapshot_enabled = 0;
if (forks && workload_exec_errno) {
char msg[STRERR_BUFSIZE];
@@ -1068,6 +1154,8 @@ struct option __record_options[] = {
OPT_CALLBACK('k', "clockid", &record.opts,
"clockid", "clockid to use for events, see clock_gettime()",
parse_clockid),
+ OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
+ "opts", "AUX area tracing Snapshot Mode", ""),
OPT_END()
};
@@ -1102,6 +1190,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
return err;
}
+ err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+ rec->opts.auxtrace_snapshot_opts);
+ if (err)
+ return err;
+
err = -ENOMEM;
symbol__init(NULL);
@@ -1165,3 +1258,12 @@ out_symbol_exit:
auxtrace_record__free(rec->itr);
return err;
}
+
+static void snapshot_sig_handler(int sig __maybe_unused)
+{
+ if (!auxtrace_snapshot_enabled)
+ return;
+ auxtrace_snapshot_enabled = 0;
+ auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
+ auxtrace_record__snapshot_started = 1;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index f0bacb6..a5d0284 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -564,6 +564,17 @@ int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
}
static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+ struct record_opts *opts __maybe_unused,
+ const char *str)
+{
+ if (!str)
+ return 0;
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
int auxtrace__process_event(struct perf_session *session __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_sample *sample __maybe_unused,
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd..367d8b8 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -123,6 +123,10 @@ struct option {
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+ .value = check_vtype(v, const char **), (a), .help = (h), \
+ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 31/44] perf auxtrace: Add Intel PT as an AUX area tracing type
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (29 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 30/44] perf record: Add AUX area tracing Snapshot Mode support Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 32/44] perf tools: Add Intel PT packet decoder Adrian Hunter
` (12 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add the Intel Processor Trace type
constant PERF_AUXTRACE_INTEL_PT.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 1 +
tools/perf/util/auxtrace.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 4373f97..e562ec3 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -885,6 +885,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
fprintf(stdout, " type: %u\n", type);
switch (type) {
+ case PERF_AUXTRACE_INTEL_PT:
case PERF_AUXTRACE_UNKNOWN:
default:
return -EINVAL;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a5d0284..ae1249a 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -39,6 +39,7 @@ struct events_stats;
enum auxtrace_type {
PERF_AUXTRACE_UNKNOWN,
+ PERF_AUXTRACE_INTEL_PT,
};
enum itrace_period_type {
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 32/44] perf tools: Add Intel PT packet decoder
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (30 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 31/44] perf auxtrace: Add Intel PT as an AUX area tracing type Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 33/44] perf tools: Add Intel PT instruction decoder Adrian Hunter
` (11 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding Intel Processor Trace
packets.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/intel-pt-decoder/Build | 1 +
.../util/intel-pt-decoder/intel-pt-pkt-decoder.c | 400 +++++++++++++++++++++
.../util/intel-pt-decoder/intel-pt-pkt-decoder.h | 64 ++++
4 files changed, 466 insertions(+)
create mode 100644 tools/perf/util/intel-pt-decoder/Build
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index c8e3590..3e790c6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -75,6 +75,7 @@ libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
new file mode 100644
index 0000000..9d67381
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -0,0 +1 @@
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
new file mode 100644
index 0000000..1c274a1
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -0,0 +1,400 @@
+/*
+ * intel_pt_pkt_decoder.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "intel-pt-pkt-decoder.h"
+
+#define BIT(n) (1 << (n))
+
+#define BIT63 ((uint64_t)1 << 63)
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define memcpy_le64(d, s, n) do { \
+ memcpy((d), (s), (n)); \
+ *(d) = le64_to_cpu(*(d)); \
+} while (0)
+#else
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define memcpy_le64 memcpy
+#endif
+
+static const char * const packet_name[] = {
+ [INTEL_PT_BAD] = "Bad Packet!",
+ [INTEL_PT_PAD] = "PAD",
+ [INTEL_PT_TNT] = "TNT",
+ [INTEL_PT_TIP_PGD] = "TIP.PGD",
+ [INTEL_PT_TIP_PGE] = "TIP.PGE",
+ [INTEL_PT_TSC] = "TSC",
+ [INTEL_PT_MODE_EXEC] = "MODE.Exec",
+ [INTEL_PT_MODE_TSX] = "MODE.TSX",
+ [INTEL_PT_TIP] = "TIP",
+ [INTEL_PT_FUP] = "FUP",
+ [INTEL_PT_PSB] = "PSB",
+ [INTEL_PT_PSBEND] = "PSBEND",
+ [INTEL_PT_CBR] = "CBR",
+ [INTEL_PT_PIP] = "PIP",
+ [INTEL_PT_OVF] = "OVF",
+};
+
+const char *intel_pt_pkt_name(enum intel_pt_pkt_type type)
+{
+ return packet_name[type];
+}
+
+static int intel_pt_get_long_tnt(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ uint64_t payload;
+ int count;
+
+ if (len < 8)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ payload = le64_to_cpu(*(uint64_t *)buf);
+
+ for (count = 47; count; count--) {
+ if (payload & BIT63)
+ break;
+ payload <<= 1;
+ }
+
+ packet->type = INTEL_PT_TNT;
+ packet->count = count;
+ packet->payload = payload << 1;
+ return 8;
+}
+
+static int intel_pt_get_pip(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ uint64_t payload = 0;
+
+ if (len < 8)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ packet->type = INTEL_PT_PIP;
+ memcpy_le64(&payload, buf + 2, 6);
+ packet->payload = payload >> 1;
+
+ return 8;
+}
+
+static int intel_pt_get_cbr(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 4)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_CBR;
+ packet->payload = buf[2];
+ return 4;
+}
+
+static int intel_pt_get_ovf(struct intel_pt_pkt *packet)
+{
+ packet->type = INTEL_PT_OVF;
+ return 2;
+}
+
+static int intel_pt_get_psb(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ int i;
+
+ if (len < 16)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ for (i = 2; i < 16; i += 2) {
+ if (buf[i] != 2 || buf[i + 1] != 0x82)
+ return INTEL_PT_BAD_PACKET;
+ }
+
+ packet->type = INTEL_PT_PSB;
+ return 16;
+}
+
+static int intel_pt_get_psbend(struct intel_pt_pkt *packet)
+{
+ packet->type = INTEL_PT_PSBEND;
+ return 2;
+}
+
+static int intel_pt_get_pad(struct intel_pt_pkt *packet)
+{
+ packet->type = INTEL_PT_PAD;
+ return 1;
+}
+
+static int intel_pt_get_ext(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 2)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ switch (buf[1]) {
+ case 0xa3: /* Long TNT */
+ return intel_pt_get_long_tnt(buf, len, packet);
+ case 0x43: /* PIP */
+ return intel_pt_get_pip(buf, len, packet);
+ case 0x03: /* CBR */
+ return intel_pt_get_cbr(buf, len, packet);
+ case 0xf3: /* OVF */
+ return intel_pt_get_ovf(packet);
+ case 0x82: /* PSB */
+ return intel_pt_get_psb(buf, len, packet);
+ case 0x23: /* PSBEND */
+ return intel_pt_get_psbend(packet);
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+}
+
+static int intel_pt_get_short_tnt(unsigned int byte,
+ struct intel_pt_pkt *packet)
+{
+ int count;
+
+ for (count = 6; count; count--) {
+ if (byte & BIT(7))
+ break;
+ byte <<= 1;
+ }
+
+ packet->type = INTEL_PT_TNT;
+ packet->count = count;
+ packet->payload = (uint64_t)byte << 57;
+
+ return 1;
+}
+
+static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
+ const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ switch (byte >> 5) {
+ case 0:
+ packet->count = 0;
+ break;
+ case 1:
+ if (len < 3)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->count = 2;
+ packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+ break;
+ case 2:
+ if (len < 5)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->count = 4;
+ packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
+ break;
+ case 3:
+ case 6:
+ if (len < 7)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->count = 6;
+ memcpy_le64(&packet->payload, buf + 1, 6);
+ break;
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+
+ packet->type = type;
+
+ return packet->count + 1;
+}
+
+static int intel_pt_get_mode(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 2)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ switch (buf[1] >> 5) {
+ case 0:
+ packet->type = INTEL_PT_MODE_EXEC;
+ switch (buf[1] & 3) {
+ case 0:
+ packet->payload = 16;
+ break;
+ case 1:
+ packet->payload = 64;
+ break;
+ case 2:
+ packet->payload = 32;
+ break;
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+ break;
+ case 1:
+ packet->type = INTEL_PT_MODE_TSX;
+ if ((buf[1] & 3) == 3)
+ return INTEL_PT_BAD_PACKET;
+ packet->payload = buf[1] & 3;
+ break;
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+
+ return 2;
+}
+
+static int intel_pt_get_tsc(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 8)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_TSC;
+ memcpy_le64(&packet->payload, buf + 1, 7);
+ return 8;
+}
+
+static int intel_pt_do_get_packet(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ unsigned int byte;
+
+ memset(packet, 0, sizeof(struct intel_pt_pkt));
+
+ if (!len)
+ return INTEL_PT_NEED_MORE_BYTES;
+
+ byte = buf[0];
+ if (!(byte & BIT(0))) {
+ if (byte == 0)
+ return intel_pt_get_pad(packet);
+ if (byte == 2)
+ return intel_pt_get_ext(buf, len, packet);
+ return intel_pt_get_short_tnt(byte, packet);
+ }
+
+ switch (byte & 0x1f) {
+ case 0x0D:
+ return intel_pt_get_ip(INTEL_PT_TIP, byte, buf, len, packet);
+ case 0x11:
+ return intel_pt_get_ip(INTEL_PT_TIP_PGE, byte, buf, len,
+ packet);
+ case 0x01:
+ return intel_pt_get_ip(INTEL_PT_TIP_PGD, byte, buf, len,
+ packet);
+ case 0x1D:
+ return intel_pt_get_ip(INTEL_PT_FUP, byte, buf, len, packet);
+ case 0x19:
+ switch (byte) {
+ case 0x99:
+ return intel_pt_get_mode(buf, len, packet);
+ case 0x19:
+ return intel_pt_get_tsc(buf, len, packet);
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+ default:
+ return INTEL_PT_BAD_PACKET;
+ }
+}
+
+int intel_pt_get_packet(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ int ret;
+
+ ret = intel_pt_do_get_packet(buf, len, packet);
+ if (ret > 0) {
+ while (ret < 8 && len > (size_t)ret && !buf[ret])
+ ret += 1;
+ }
+ return ret;
+}
+
+int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
+ size_t buf_len)
+{
+ int ret, i;
+ unsigned long long payload = packet->payload;
+ const char *name = intel_pt_pkt_name(packet->type);
+
+ switch (packet->type) {
+ case INTEL_PT_BAD:
+ case INTEL_PT_PAD:
+ case INTEL_PT_PSB:
+ case INTEL_PT_PSBEND:
+ case INTEL_PT_OVF:
+ return snprintf(buf, buf_len, "%s", name);
+ case INTEL_PT_TNT: {
+ size_t blen = buf_len;
+
+ ret = snprintf(buf, blen, "%s ", name);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ blen -= ret;
+ for (i = 0; i < packet->count; i++) {
+ if (payload & BIT63)
+ ret = snprintf(buf, blen, "T");
+ else
+ ret = snprintf(buf, blen, "N");
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ blen -= ret;
+ payload <<= 1;
+ }
+ ret = snprintf(buf, blen, " (%d)", packet->count);
+ if (ret < 0)
+ return ret;
+ blen -= ret;
+ return buf_len - blen;
+ }
+ case INTEL_PT_TIP_PGD:
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_TIP:
+ case INTEL_PT_FUP:
+ if (!(packet->count))
+ return snprintf(buf, buf_len, "%s no ip", name);
+ case INTEL_PT_CBR:
+ return snprintf(buf, buf_len, "%s 0x%llx", name, payload);
+ case INTEL_PT_TSC:
+ if (packet->count)
+ return snprintf(buf, buf_len,
+ "%s 0x%llx CTC 0x%x FC 0x%x",
+ name, payload, packet->count & 0xffff,
+ (packet->count >> 16) & 0x1ff);
+ else
+ return snprintf(buf, buf_len, "%s 0x%llx",
+ name, payload);
+ case INTEL_PT_MODE_EXEC:
+ return snprintf(buf, buf_len, "%s %lld", name, payload);
+ case INTEL_PT_MODE_TSX:
+ return snprintf(buf, buf_len, "%s TXAbort:%u InTX:%u",
+ name, (unsigned)(payload >> 1) & 1,
+ (unsigned)payload & 1);
+ case INTEL_PT_PIP:
+ ret = snprintf(buf, buf_len, "%s 0x%llx",
+ name, payload);
+ return ret;
+ default:
+ break;
+ }
+ return snprintf(buf, buf_len, "%s 0x%llx (%d)",
+ name, payload, packet->count);
+}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
new file mode 100644
index 0000000..53404fa
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
@@ -0,0 +1,64 @@
+/*
+ * intel_pt_pkt_decoder.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__INTEL_PT_PKT_DECODER_H__
+#define INCLUDE__INTEL_PT_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define INTEL_PT_PKT_DESC_MAX 256
+
+#define INTEL_PT_NEED_MORE_BYTES -1
+#define INTEL_PT_BAD_PACKET -2
+
+#define INTEL_PT_PSB_STR "\002\202\002\202\002\202\002\202" \
+ "\002\202\002\202\002\202\002\202"
+#define INTEL_PT_PSB_LEN 16
+
+#define INTEL_PT_PKT_MAX_SZ 16
+
+enum intel_pt_pkt_type {
+ INTEL_PT_BAD,
+ INTEL_PT_PAD,
+ INTEL_PT_TNT,
+ INTEL_PT_TIP_PGD,
+ INTEL_PT_TIP_PGE,
+ INTEL_PT_TSC,
+ INTEL_PT_MODE_EXEC,
+ INTEL_PT_MODE_TSX,
+ INTEL_PT_TIP,
+ INTEL_PT_FUP,
+ INTEL_PT_PSB,
+ INTEL_PT_PSBEND,
+ INTEL_PT_CBR,
+ INTEL_PT_PIP,
+ INTEL_PT_OVF,
+};
+
+struct intel_pt_pkt {
+ enum intel_pt_pkt_type type;
+ int count;
+ uint64_t payload;
+};
+
+const char *intel_pt_pkt_name(enum intel_pt_pkt_type);
+
+int intel_pt_get_packet(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet);
+
+int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, size_t len);
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 33/44] perf tools: Add Intel PT instruction decoder
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (31 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 32/44] perf tools: Add Intel PT packet decoder Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 34/44] perf tools: Add Intel PT log Adrian Hunter
` (10 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding instructions for Intel
Processor Trace. The kernel x86 instruction
decoder is used for this.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/build/Makefile.build | 2 +
tools/perf/.gitignore | 2 +
tools/perf/Makefile.perf | 6 +-
tools/perf/util/intel-pt-decoder/Build | 15 +-
.../util/intel-pt-decoder/intel-pt-insn-decoder.c | 246 +++++++++++++++++++++
.../util/intel-pt-decoder/intel-pt-insn-decoder.h | 65 ++++++
6 files changed, 333 insertions(+), 3 deletions(-)
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 10df572..7ad74e4 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -57,6 +57,8 @@ quiet_cmd_cc_i_c = CPP $@
quiet_cmd_cc_s_c = AS $@
cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
+quiet_cmd_gen = GEN $@
+
# Link agregate command
# If there's nothing to link, create empty $@ object.
quiet_cmd_ld_multi = LD $@
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 812f904..c88d5c5 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -28,3 +28,5 @@ config.mak.autogen
*-flex.*
*.pyc
*.pyo
+util/intel-pt-decoder/inat-tables.c
+util/intel-pt-decoder/inat.c
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 03409cc..0699220 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -122,6 +122,7 @@ INSTALL = install
FLEX = flex
BISON = bison
STRIP = strip
+AWK = awk
LIB_DIR = $(srctree)/tools/lib/api/
TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
@@ -272,7 +273,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf
PERF_IN := $(OUTPUT)perf-in.o
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX
+export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
build := -f $(srctree)/tools/build/Makefile.build dir=. obj
$(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE
@@ -532,7 +533,8 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
$(Q)$(RM) .config-detected
$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
- $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+ $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
+ $(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
$(python-clean)
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 9d67381..b608469 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1 +1,14 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+
+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
+
+$(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+ @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
+
+$(OUTPUT)util/intel-pt-decoder/inat.c:
+ @$(call echo-cmd,gen)cp ../../arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat.c
+
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: $(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+
+CFLAGS_intel-pt-insn-decoder.o += -I../../arch/x86/include -I$(OUTPUT)util/intel-pt-decoder -I../../arch/x86/lib
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
new file mode 100644
index 0000000..2fa82c5
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -0,0 +1,246 @@
+/*
+ * intel_pt_insn_decoder.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "event.h"
+
+#include <asm/insn.h>
+
+#include "inat.c"
+#include <insn.c>
+
+#include "intel-pt-insn-decoder.h"
+
+/* Based on branch_type() from perf_event_intel_lbr.c */
+static void intel_pt_insn_decoder(struct insn *insn,
+ struct intel_pt_insn *intel_pt_insn)
+{
+ enum intel_pt_insn_op op = INTEL_PT_OP_OTHER;
+ enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
+ int ext;
+
+ if (insn_is_avx(insn)) {
+ intel_pt_insn->op = INTEL_PT_OP_OTHER;
+ intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
+ intel_pt_insn->length = insn->length;
+ return;
+ }
+
+ switch (insn->opcode.bytes[0]) {
+ case 0xf:
+ switch (insn->opcode.bytes[1]) {
+ case 0x05: /* syscall */
+ case 0x34: /* sysenter */
+ op = INTEL_PT_OP_SYSCALL;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0x07: /* sysret */
+ case 0x35: /* sysexit */
+ op = INTEL_PT_OP_SYSRET;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0x80 ... 0x8f: /* jcc */
+ op = INTEL_PT_OP_JCC;
+ branch = INTEL_PT_BR_CONDITIONAL;
+ break;
+ default:
+ break;
+ }
+ break;
+ case 0x70 ... 0x7f: /* jcc */
+ op = INTEL_PT_OP_JCC;
+ branch = INTEL_PT_BR_CONDITIONAL;
+ break;
+ case 0xc2: /* near ret */
+ case 0xc3: /* near ret */
+ case 0xca: /* far ret */
+ case 0xcb: /* far ret */
+ op = INTEL_PT_OP_RET;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0xcf: /* iret */
+ op = INTEL_PT_OP_IRET;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0xcc ... 0xce: /* int */
+ op = INTEL_PT_OP_INT;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0xe8: /* call near rel */
+ op = INTEL_PT_OP_CALL;
+ branch = INTEL_PT_BR_UNCONDITIONAL;
+ break;
+ case 0x9a: /* call far absolute */
+ op = INTEL_PT_OP_CALL;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0xe0 ... 0xe2: /* loop */
+ op = INTEL_PT_OP_LOOP;
+ branch = INTEL_PT_BR_CONDITIONAL;
+ break;
+ case 0xe3: /* jcc */
+ op = INTEL_PT_OP_JCC;
+ branch = INTEL_PT_BR_CONDITIONAL;
+ break;
+ case 0xe9: /* jmp */
+ case 0xeb: /* jmp */
+ op = INTEL_PT_OP_JMP;
+ branch = INTEL_PT_BR_UNCONDITIONAL;
+ break;
+ case 0xea: /* far jmp */
+ op = INTEL_PT_OP_JMP;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 0xff: /* call near absolute, call far absolute ind */
+ ext = (insn->modrm.bytes[0] >> 3) & 0x7;
+ switch (ext) {
+ case 2: /* near ind call */
+ case 3: /* far ind call */
+ op = INTEL_PT_OP_CALL;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ case 4:
+ case 5:
+ op = INTEL_PT_OP_JMP;
+ branch = INTEL_PT_BR_INDIRECT;
+ break;
+ default:
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+
+ intel_pt_insn->op = op;
+ intel_pt_insn->branch = branch;
+ intel_pt_insn->length = insn->length;
+
+ if (branch == INTEL_PT_BR_CONDITIONAL ||
+ branch == INTEL_PT_BR_UNCONDITIONAL) {
+#if __BYTE_ORDER == __BIG_ENDIAN
+ switch (insn->immediate.nbytes) {
+ case 1:
+ intel_pt_insn->rel = insn->immediate.value;
+ break;
+ case 2:
+ intel_pt_insn->rel =
+ bswap_16((short)insn->immediate.value);
+ break;
+ case 4:
+ intel_pt_insn->rel = bswap_32(insn->immediate.value);
+ break;
+ }
+#else
+ intel_pt_insn->rel = insn->immediate.value;
+#endif
+ }
+}
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+ struct intel_pt_insn *intel_pt_insn)
+{
+ struct insn insn;
+
+ insn_init(&insn, buf, len, x86_64);
+ insn_get_length(&insn);
+ if (!insn_complete(&insn) || insn.length > len)
+ return -1;
+ intel_pt_insn_decoder(&insn, intel_pt_insn);
+ if (insn.length < INTEL_PT_INSN_DBG_BUF_SZ)
+ memcpy(intel_pt_insn->buf, buf, insn.length);
+ else
+ memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_DBG_BUF_SZ);
+ return 0;
+}
+
+const char *branch_name[] = {
+ [INTEL_PT_OP_OTHER] = "Other",
+ [INTEL_PT_OP_CALL] = "Call",
+ [INTEL_PT_OP_RET] = "Ret",
+ [INTEL_PT_OP_JCC] = "Jcc",
+ [INTEL_PT_OP_JMP] = "Jmp",
+ [INTEL_PT_OP_LOOP] = "Loop",
+ [INTEL_PT_OP_IRET] = "IRet",
+ [INTEL_PT_OP_INT] = "Int",
+ [INTEL_PT_OP_SYSCALL] = "Syscall",
+ [INTEL_PT_OP_SYSRET] = "Sysret",
+};
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op)
+{
+ return branch_name[op];
+}
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+ size_t buf_len)
+{
+ switch (intel_pt_insn->branch) {
+ case INTEL_PT_BR_CONDITIONAL:
+ case INTEL_PT_BR_UNCONDITIONAL:
+ return snprintf(buf, buf_len, "%s %s%d",
+ intel_pt_insn_name(intel_pt_insn->op),
+ intel_pt_insn->rel > 0 ? "+" : "",
+ intel_pt_insn->rel);
+ case INTEL_PT_BR_NO_BRANCH:
+ case INTEL_PT_BR_INDIRECT:
+ return snprintf(buf, buf_len, "%s",
+ intel_pt_insn_name(intel_pt_insn->op));
+ default:
+ break;
+ }
+ return 0;
+}
+
+size_t intel_pt_insn_max_size(void)
+{
+ return MAX_INSN_SIZE;
+}
+
+int intel_pt_insn_type(enum intel_pt_insn_op op)
+{
+ switch (op) {
+ case INTEL_PT_OP_OTHER:
+ return 0;
+ case INTEL_PT_OP_CALL:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL;
+ case INTEL_PT_OP_RET:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN;
+ case INTEL_PT_OP_JCC:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+ case INTEL_PT_OP_JMP:
+ return PERF_IP_FLAG_BRANCH;
+ case INTEL_PT_OP_LOOP:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+ case INTEL_PT_OP_IRET:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+ PERF_IP_FLAG_INTERRUPT;
+ case INTEL_PT_OP_INT:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+ PERF_IP_FLAG_INTERRUPT;
+ case INTEL_PT_OP_SYSCALL:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+ PERF_IP_FLAG_SYSCALLRET;
+ case INTEL_PT_OP_SYSRET:
+ return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+ PERF_IP_FLAG_SYSCALLRET;
+ default:
+ return 0;
+ }
+}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
new file mode 100644
index 0000000..b0adbf3
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
@@ -0,0 +1,65 @@
+/*
+ * intel_pt_insn_decoder.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__INTEL_PT_INSN_DECODER_H__
+#define INCLUDE__INTEL_PT_INSN_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define INTEL_PT_INSN_DESC_MAX 32
+#define INTEL_PT_INSN_DBG_BUF_SZ 16
+
+enum intel_pt_insn_op {
+ INTEL_PT_OP_OTHER,
+ INTEL_PT_OP_CALL,
+ INTEL_PT_OP_RET,
+ INTEL_PT_OP_JCC,
+ INTEL_PT_OP_JMP,
+ INTEL_PT_OP_LOOP,
+ INTEL_PT_OP_IRET,
+ INTEL_PT_OP_INT,
+ INTEL_PT_OP_SYSCALL,
+ INTEL_PT_OP_SYSRET,
+};
+
+enum intel_pt_insn_branch {
+ INTEL_PT_BR_NO_BRANCH,
+ INTEL_PT_BR_INDIRECT,
+ INTEL_PT_BR_CONDITIONAL,
+ INTEL_PT_BR_UNCONDITIONAL,
+};
+
+struct intel_pt_insn {
+ enum intel_pt_insn_op op;
+ enum intel_pt_insn_branch branch;
+ int length;
+ int32_t rel;
+ unsigned char buf[INTEL_PT_INSN_DBG_BUF_SZ];
+};
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+ struct intel_pt_insn *intel_pt_insn);
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op);
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+ size_t buf_len);
+
+size_t intel_pt_insn_max_size(void);
+
+int intel_pt_insn_type(enum intel_pt_insn_op op);
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 34/44] perf tools: Add Intel PT log
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (32 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 33/44] perf tools: Add Intel PT instruction decoder Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 35/44] perf tools: Add Intel PT decoder Adrian Hunter
` (9 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add a facility to log Intel Processor Trace
decoding. The log is intended for debugging
purposes only.
The log file name is "intel_pt.log" and is
opened in the current directory.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-pt-decoder/Build | 2 +-
tools/perf/util/intel-pt-decoder/intel-pt-log.c | 155 ++++++++++++++++++++++++
tools/perf/util/intel-pt-decoder/intel-pt-log.h | 52 ++++++++
3 files changed, 208 insertions(+), 1 deletion(-)
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-log.c
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-log.h
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index b608469..a8cf6df 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o
inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
new file mode 100644
index 0000000..d09c7d9
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -0,0 +1,155 @@
+/*
+ * intel_pt_log.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <string.h>
+
+#include "intel-pt-log.h"
+#include "intel-pt-insn-decoder.h"
+
+#include "intel-pt-pkt-decoder.h"
+
+#define MAX_LOG_NAME 256
+
+static FILE *f;
+static char log_name[MAX_LOG_NAME];
+static bool enable_logging;
+
+void intel_pt_log_enable(void)
+{
+ enable_logging = true;
+}
+
+void intel_pt_log_disable(void)
+{
+ if (f)
+ fflush(f);
+ enable_logging = false;
+}
+
+void intel_pt_log_set_name(const char *name)
+{
+ strncpy(log_name, name, MAX_LOG_NAME - 5);
+ strcat(log_name, ".log");
+}
+
+static void intel_pt_print_data(const unsigned char *buf, int len, uint64_t pos,
+ int indent)
+{
+ int i;
+
+ for (i = 0; i < indent; i++)
+ fprintf(f, " ");
+
+ fprintf(f, " %08" PRIx64 ": ", pos);
+ for (i = 0; i < len; i++)
+ fprintf(f, " %02x", buf[i]);
+ for (; i < 16; i++)
+ fprintf(f, " ");
+ fprintf(f, " ");
+}
+
+static void intel_pt_print_no_data(uint64_t pos, int indent)
+{
+ int i;
+
+ for (i = 0; i < indent; i++)
+ fprintf(f, " ");
+
+ fprintf(f, " %08" PRIx64 ": ", pos);
+ for (i = 0; i < 16; i++)
+ fprintf(f, " ");
+ fprintf(f, " ");
+}
+
+static int intel_pt_log_open(void)
+{
+ if (!enable_logging)
+ return -1;
+
+ if (f)
+ return 0;
+
+ if (!log_name[0])
+ return -1;
+
+ f = fopen(log_name, "w+");
+ if (!f) {
+ enable_logging = false;
+ return -1;
+ }
+
+ return 0;
+}
+
+void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+ uint64_t pos, const unsigned char *buf)
+{
+ char desc[INTEL_PT_PKT_DESC_MAX];
+
+ if (intel_pt_log_open())
+ return;
+
+ intel_pt_print_data(buf, pkt_len, pos, 0);
+ intel_pt_pkt_desc(packet, desc, INTEL_PT_PKT_DESC_MAX);
+ fprintf(f, "%s\n", desc);
+}
+
+void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+{
+ char desc[INTEL_PT_INSN_DESC_MAX];
+ size_t len = intel_pt_insn->length;
+
+ if (intel_pt_log_open())
+ return;
+
+ if (len > INTEL_PT_INSN_DBG_BUF_SZ)
+ len = INTEL_PT_INSN_DBG_BUF_SZ;
+ intel_pt_print_data(intel_pt_insn->buf, len, ip, 8);
+ if (intel_pt_insn_desc(intel_pt_insn, desc, INTEL_PT_INSN_DESC_MAX) > 0)
+ fprintf(f, "%s\n", desc);
+ else
+ fprintf(f, "Bad instruction!\n");
+}
+
+void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+{
+ char desc[INTEL_PT_INSN_DESC_MAX];
+
+ if (intel_pt_log_open())
+ return;
+
+ intel_pt_print_no_data(ip, 8);
+ if (intel_pt_insn_desc(intel_pt_insn, desc, INTEL_PT_INSN_DESC_MAX) > 0)
+ fprintf(f, "%s\n", desc);
+ else
+ fprintf(f, "Bad instruction!\n");
+}
+
+void intel_pt_log(const char *fmt, ...)
+{
+ va_list args;
+
+ if (intel_pt_log_open())
+ return;
+
+ va_start(args, fmt);
+ vfprintf(f, fmt, args);
+ va_end(args);
+}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
new file mode 100644
index 0000000..db3942f
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -0,0 +1,52 @@
+/*
+ * intel_pt_log.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__INTEL_PT_LOG_H__
+#define INCLUDE__INTEL_PT_LOG_H__
+
+#include <stdint.h>
+#include <inttypes.h>
+
+struct intel_pt_pkt;
+
+void intel_pt_log_enable(void);
+void intel_pt_log_disable(void);
+void intel_pt_log_set_name(const char *name);
+
+void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+ uint64_t pos, const unsigned char *buf);
+
+struct intel_pt_insn;
+
+void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
+void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
+ uint64_t ip);
+
+__attribute__((format(printf, 1, 2)))
+void intel_pt_log(const char *fmt, ...);
+
+#define x64_fmt "0x%" PRIx64
+
+static inline void intel_pt_log_at(const char *msg, uint64_t u)
+{
+ intel_pt_log("%s at " x64_fmt "\n", msg, u);
+}
+
+static inline void intel_pt_log_to(const char *msg, uint64_t u)
+{
+ intel_pt_log("%s to " x64_fmt "\n", msg, u);
+}
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 35/44] perf tools: Add Intel PT decoder
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (33 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 34/44] perf tools: Add Intel PT log Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 36/44] perf tools: Add Intel PT support Adrian Hunter
` (8 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for decoding an Intel Processor Trace.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-pt-decoder/Build | 2 +-
.../perf/util/intel-pt-decoder/intel-pt-decoder.c | 1738 ++++++++++++++++++++
.../perf/util/intel-pt-decoder/intel-pt-decoder.h | 89 +
3 files changed, 1828 insertions(+), 1 deletion(-)
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index a8cf6df..74d6feb 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
new file mode 100644
index 0000000..16e5efb
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -0,0 +1,1738 @@
+/*
+ * intel_pt_decoder.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <stdint.h>
+#include <inttypes.h>
+
+#include "intel-pt-insn-decoder.h"
+#include "intel-pt-pkt-decoder.h"
+#include "intel-pt-decoder.h"
+#include "intel-pt-log.h"
+
+#define INTEL_PT_BLK_SIZE 1024
+
+#define BIT63 (((uint64_t)1 << 63))
+
+#define INTEL_PT_RETURN 1
+
+struct intel_pt_blk {
+ struct intel_pt_blk *prev;
+ uint64_t ip[INTEL_PT_BLK_SIZE];
+};
+
+struct intel_pt_stack {
+ struct intel_pt_blk *blk;
+ struct intel_pt_blk *spare;
+ int pos;
+};
+
+enum intel_pt_pkt_state {
+ INTEL_PT_STATE_NO_PSB,
+ INTEL_PT_STATE_NO_IP,
+ INTEL_PT_STATE_ERR_RESYNC,
+ INTEL_PT_STATE_IN_SYNC,
+ INTEL_PT_STATE_TNT,
+ INTEL_PT_STATE_TIP,
+ INTEL_PT_STATE_TIP_PGD,
+ INTEL_PT_STATE_FUP,
+ INTEL_PT_STATE_FUP_NO_TIP,
+};
+
+#ifdef INTEL_PT_STRICT
+#define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB
+#define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB
+#define INTEL_PT_STATE_ERR3 INTEL_PT_STATE_NO_PSB
+#define INTEL_PT_STATE_ERR4 INTEL_PT_STATE_NO_PSB
+#else
+#define INTEL_PT_STATE_ERR1 (decoder->pkt_state)
+#define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_IP
+#define INTEL_PT_STATE_ERR3 INTEL_PT_STATE_ERR_RESYNC
+#define INTEL_PT_STATE_ERR4 INTEL_PT_STATE_IN_SYNC
+#endif
+
+struct intel_pt_decoder {
+ int (*get_trace)(struct intel_pt_buffer *buffer, void *data);
+ int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
+ uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
+ uint64_t max_insn_cnt, void *data);
+ void *data;
+ struct intel_pt_state state;
+ const unsigned char *buf;
+ size_t len;
+ bool return_compression;
+ bool pge;
+ uint64_t pos;
+ uint64_t last_ip;
+ uint64_t ip;
+ uint64_t cr3;
+ uint64_t timestamp;
+ uint64_t tsc_timestamp;
+ uint64_t ref_timestamp;
+ uint64_t ret_addr;
+ struct intel_pt_stack stack;
+ enum intel_pt_pkt_state pkt_state;
+ struct intel_pt_pkt packet;
+ struct intel_pt_pkt tnt;
+ int pkt_step;
+ int pkt_len;
+ unsigned int cbr;
+ int exec_mode;
+ unsigned int insn_bytes;
+ uint64_t sign_bit;
+ uint64_t sign_bits;
+ uint64_t period;
+ enum intel_pt_period_type period_type;
+ uint64_t period_insn_cnt;
+ uint64_t period_mask;
+ uint64_t period_ticks;
+ uint64_t last_masked_timestamp;
+ bool continuous_period;
+ bool overflow;
+ bool set_fup_tx_flags;
+ unsigned int fup_tx_flags;
+ unsigned int tx_flags;
+ uint64_t timestamp_insn_cnt;
+ const unsigned char *next_buf;
+ size_t next_len;
+ unsigned char temp_buf[INTEL_PT_PKT_MAX_SZ];
+};
+
+static uint64_t intel_pt_lower_power_of_2(uint64_t x)
+{
+ int i;
+
+ for (i = 0; x != 1; i++)
+ x >>= 1;
+
+ return x << i;
+}
+
+static void intel_pt_setup_period(struct intel_pt_decoder *decoder)
+{
+ if (decoder->period_type == INTEL_PT_PERIOD_TICKS) {
+ uint64_t period;
+
+ period = intel_pt_lower_power_of_2(decoder->period);
+ decoder->period_mask = ~(period - 1);
+ decoder->period_ticks = period;
+ }
+}
+
+struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
+{
+ struct intel_pt_decoder *decoder;
+
+ if (!params->get_trace || !params->walk_insn)
+ return NULL;
+
+ decoder = malloc(sizeof(struct intel_pt_decoder));
+ if (!decoder)
+ return NULL;
+
+ memset(decoder, 0, sizeof(struct intel_pt_decoder));
+
+ decoder->get_trace = params->get_trace;
+ decoder->walk_insn = params->walk_insn;
+ decoder->data = params->data;
+ decoder->return_compression = params->return_compression;
+
+ decoder->sign_bit = (uint64_t)1 << 47;
+ decoder->sign_bits = ~(((uint64_t)1 << 48) - 1);
+
+ decoder->period = params->period;
+ decoder->period_type = params->period_type;
+
+ intel_pt_setup_period(decoder);
+
+ return decoder;
+}
+
+static void intel_pt_pop_blk(struct intel_pt_stack *stack)
+{
+ struct intel_pt_blk *blk;
+
+ blk = stack->blk;
+ stack->blk = blk->prev;
+ if (!stack->spare)
+ stack->spare = blk;
+ else
+ free(blk);
+}
+
+static uint64_t intel_pt_pop(struct intel_pt_stack *stack)
+{
+ if (!stack->pos) {
+ if (!stack->blk)
+ return 0;
+ intel_pt_pop_blk(stack);
+ if (!stack->blk)
+ return 0;
+ stack->pos = INTEL_PT_BLK_SIZE;
+ }
+ return stack->blk->ip[--stack->pos];
+}
+
+static int intel_pt_alloc_blk(struct intel_pt_stack *stack)
+{
+ struct intel_pt_blk *blk;
+
+ if (stack->spare) {
+ blk = stack->spare;
+ stack->spare = NULL;
+ } else {
+ blk = malloc(sizeof(struct intel_pt_blk));
+ if (!blk)
+ return -ENOMEM;
+ }
+
+ blk->prev = stack->blk;
+ stack->blk = blk;
+ stack->pos = 0;
+ return 0;
+}
+
+static int intel_pt_push(struct intel_pt_stack *stack, uint64_t ip)
+{
+ int err;
+
+ if (!stack->blk || stack->pos == INTEL_PT_BLK_SIZE) {
+ err = intel_pt_alloc_blk(stack);
+ if (err)
+ return err;
+ }
+
+ stack->blk->ip[stack->pos++] = ip;
+ return 0;
+}
+
+static void intel_pt_clear_stack(struct intel_pt_stack *stack)
+{
+ while (stack->blk)
+ intel_pt_pop_blk(stack);
+ stack->pos = 0;
+}
+
+static void intel_pt_free_stack(struct intel_pt_stack *stack)
+{
+ intel_pt_clear_stack(stack);
+ free(stack->blk);
+ free(stack->spare);
+}
+
+void intel_pt_decoder_free(struct intel_pt_decoder *decoder)
+{
+ intel_pt_free_stack(&decoder->stack);
+ free(decoder);
+}
+
+const char *intel_pt_error_message(int code)
+{
+ switch (code) {
+ case ENOMEM:
+ return "Memory allocation failed";
+ case ENOSYS:
+ return "Internal error";
+ case EBADMSG:
+ return "Bad packet";
+ case ENODATA:
+ return "No more data";
+ case EILSEQ:
+ return "Failed to get instruction";
+ case ENOENT:
+ return "Trace doesn't match instruction";
+ case EOVERFLOW:
+ return "Overflow packet";
+ case ESHUTDOWN:
+ return "Trace stop packet";
+ default:
+ return "Unknown error!";
+ }
+}
+
+static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
+ const struct intel_pt_pkt *packet,
+ uint64_t last_ip)
+{
+ uint64_t ip;
+
+ switch (packet->count) {
+ case 2:
+ ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
+ packet->payload;
+ break;
+ case 4:
+ ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
+ packet->payload;
+ break;
+ case 6:
+ ip = packet->payload;
+ break;
+ default:
+ return 0;
+ }
+
+ if (ip & decoder->sign_bit)
+ return ip | decoder->sign_bits;
+
+ return ip;
+}
+
+static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
+{
+ decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
+ decoder->last_ip);
+}
+
+static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
+{
+ intel_pt_set_last_ip(decoder);
+ decoder->ip = decoder->last_ip;
+}
+
+static void intel_pt_decoder_log_packet(struct intel_pt_decoder *decoder)
+{
+ intel_pt_log_packet(&decoder->packet, decoder->pkt_len, decoder->pos,
+ decoder->buf);
+}
+
+static int intel_pt_bug(struct intel_pt_decoder *decoder)
+{
+ intel_pt_log("ERROR: Internal error\n");
+ decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+ return -ENOSYS;
+}
+
+static inline void intel_pt_clear_tx_flags(struct intel_pt_decoder *decoder)
+{
+ decoder->tx_flags = 0;
+}
+
+static inline void intel_pt_update_in_tx(struct intel_pt_decoder *decoder)
+{
+ decoder->tx_flags = decoder->packet.payload & INTEL_PT_IN_TX;
+}
+
+static int intel_pt_bad_packet(struct intel_pt_decoder *decoder)
+{
+ intel_pt_clear_tx_flags(decoder);
+ decoder->pkt_len = 1;
+ decoder->pkt_step = 1;
+ intel_pt_decoder_log_packet(decoder);
+ if (decoder->pkt_state != INTEL_PT_STATE_NO_PSB) {
+ intel_pt_log("ERROR: Bad packet\n");
+ decoder->pkt_state = INTEL_PT_STATE_ERR1;
+ }
+ return -EBADMSG;
+}
+
+static int intel_pt_get_data(struct intel_pt_decoder *decoder)
+{
+ struct intel_pt_buffer buffer = {0};
+ int ret;
+
+ decoder->pkt_step = 0;
+
+ intel_pt_log("Getting more data\n");
+ ret = decoder->get_trace(&buffer, decoder->data);
+ if (ret)
+ return ret;
+ decoder->buf = buffer.buf;
+ decoder->len = buffer.len;
+ if (!decoder->len) {
+ intel_pt_log("No more data\n");
+ return -ENODATA;
+ }
+ if (!buffer.consecutive) {
+ decoder->ip = 0;
+ decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+ decoder->ref_timestamp = buffer.ref_timestamp;
+ decoder->timestamp = 0;
+ decoder->state.trace_nr = buffer.trace_nr;
+ intel_pt_log("Reference timestamp 0x%" PRIx64 "\n",
+ decoder->ref_timestamp);
+ return -ENOLINK;
+ }
+
+ return 0;
+}
+
+static int intel_pt_get_next_data(struct intel_pt_decoder *decoder)
+{
+ if (!decoder->next_buf)
+ return intel_pt_get_data(decoder);
+
+ decoder->buf = decoder->next_buf;
+ decoder->len = decoder->next_len;
+ decoder->next_buf = 0;
+ decoder->next_len = 0;
+ return 0;
+}
+
+static int intel_pt_get_split_packet(struct intel_pt_decoder *decoder)
+{
+ unsigned char *buf = decoder->temp_buf;
+ size_t old_len, len, n;
+ int ret;
+
+ old_len = decoder->len;
+ len = decoder->len;
+ memcpy(buf, decoder->buf, len);
+
+ ret = intel_pt_get_data(decoder);
+ if (ret) {
+ decoder->pos += old_len;
+ return ret < 0 ? ret : -EINVAL;
+ }
+
+ n = INTEL_PT_PKT_MAX_SZ - len;
+ if (n > decoder->len)
+ n = decoder->len;
+ memcpy(buf + len, decoder->buf, n);
+ len += n;
+
+ ret = intel_pt_get_packet(buf, len, &decoder->packet);
+ if (ret < (int)old_len) {
+ decoder->next_buf = decoder->buf;
+ decoder->next_len = decoder->len;
+ decoder->buf = buf;
+ decoder->len = old_len;
+ return intel_pt_bad_packet(decoder);
+ }
+
+ decoder->next_buf = decoder->buf + (ret - old_len);
+ decoder->next_len = decoder->len - (ret - old_len);
+
+ decoder->buf = buf;
+ decoder->len = ret;
+
+ return ret;
+}
+
+static int intel_pt_get_next_packet(struct intel_pt_decoder *decoder)
+{
+ int ret;
+
+ do {
+ decoder->pos += decoder->pkt_step;
+ decoder->buf += decoder->pkt_step;
+ decoder->len -= decoder->pkt_step;
+
+ if (!decoder->len) {
+ ret = intel_pt_get_next_data(decoder);
+ if (ret)
+ return ret;
+ }
+
+ ret = intel_pt_get_packet(decoder->buf, decoder->len,
+ &decoder->packet);
+ if (ret == INTEL_PT_NEED_MORE_BYTES &&
+ decoder->len < INTEL_PT_PKT_MAX_SZ && !decoder->next_buf) {
+ ret = intel_pt_get_split_packet(decoder);
+ if (ret < 0)
+ return ret;
+ }
+ if (ret <= 0)
+ return intel_pt_bad_packet(decoder);
+
+ decoder->pkt_len = ret;
+ decoder->pkt_step = ret;
+ intel_pt_decoder_log_packet(decoder);
+ } while (decoder->packet.type == INTEL_PT_PAD);
+
+ return 0;
+}
+
+static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder)
+{
+ uint64_t timestamp, masked_timestamp;
+
+ timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
+ masked_timestamp = timestamp & decoder->period_mask;
+ if (decoder->continuous_period) {
+ if (masked_timestamp != decoder->last_masked_timestamp)
+ return 1;
+ } else {
+ timestamp += 1;
+ masked_timestamp = timestamp & decoder->period_mask;
+ if (masked_timestamp != decoder->last_masked_timestamp) {
+ decoder->last_masked_timestamp = masked_timestamp;
+ decoder->continuous_period = true;
+ }
+ }
+ return decoder->period_ticks - (timestamp - masked_timestamp);
+}
+
+static uint64_t intel_pt_next_sample(struct intel_pt_decoder *decoder)
+{
+ switch (decoder->period_type) {
+ case INTEL_PT_PERIOD_INSTRUCTIONS:
+ return decoder->period - decoder->period_insn_cnt;
+ case INTEL_PT_PERIOD_TICKS:
+ return intel_pt_next_period(decoder);
+ case INTEL_PT_PERIOD_NONE:
+ default:
+ return 0;
+ }
+}
+
+static void intel_pt_sample_insn(struct intel_pt_decoder *decoder)
+{
+ uint64_t timestamp, masked_timestamp;
+
+ switch (decoder->period_type) {
+ case INTEL_PT_PERIOD_INSTRUCTIONS:
+ decoder->period_insn_cnt = 0;
+ break;
+ case INTEL_PT_PERIOD_TICKS:
+ timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
+ masked_timestamp = timestamp & decoder->period_mask;
+ decoder->last_masked_timestamp = masked_timestamp;
+ break;
+ case INTEL_PT_PERIOD_NONE:
+ default:
+ break;
+ }
+
+ decoder->state.type |= INTEL_PT_INSTRUCTION;
+}
+
+static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
+ struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+{
+ uint64_t max_insn_cnt, insn_cnt = 0;
+ int err;
+
+ max_insn_cnt = intel_pt_next_sample(decoder);
+
+ err = decoder->walk_insn(intel_pt_insn, &insn_cnt, &decoder->ip, ip,
+ max_insn_cnt, decoder->data);
+
+ decoder->timestamp_insn_cnt += insn_cnt;
+ decoder->period_insn_cnt += insn_cnt;
+
+ if (err) {
+ decoder->pkt_state = INTEL_PT_STATE_ERR2;
+ intel_pt_log_at("ERROR: Failed to get instruction",
+ decoder->ip);
+ if (err == -ENOENT)
+ return -ENOLINK;
+ return -EILSEQ;
+ }
+
+ if (ip && decoder->ip == ip) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ if (max_insn_cnt && insn_cnt >= max_insn_cnt)
+ intel_pt_sample_insn(decoder);
+
+ if (intel_pt_insn->branch == INTEL_PT_BR_NO_BRANCH) {
+ decoder->state.type = INTEL_PT_INSTRUCTION;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ decoder->ip += intel_pt_insn->length;
+ err = INTEL_PT_RETURN;
+ goto out;
+ }
+
+ if (intel_pt_insn->op == INTEL_PT_OP_CALL) {
+ /* Zero-length calls are excluded */
+ if (intel_pt_insn->branch != INTEL_PT_BR_UNCONDITIONAL ||
+ intel_pt_insn->rel) {
+ err = intel_pt_push(&decoder->stack, decoder->ip +
+ intel_pt_insn->length);
+ if (err)
+ goto out;
+ }
+ } else if (intel_pt_insn->op == INTEL_PT_OP_RET) {
+ decoder->ret_addr = intel_pt_pop(&decoder->stack);
+ }
+
+ if (intel_pt_insn->branch == INTEL_PT_BR_UNCONDITIONAL) {
+ decoder->state.from_ip = decoder->ip;
+ decoder->ip += intel_pt_insn->length +
+ intel_pt_insn->rel;
+ decoder->state.to_ip = decoder->ip;
+ err = INTEL_PT_RETURN;
+ }
+out:
+ decoder->state.insn_op = intel_pt_insn->op;
+ decoder->state.insn_len = intel_pt_insn->length;
+
+ if (decoder->tx_flags & INTEL_PT_IN_TX)
+ decoder->state.flags |= INTEL_PT_IN_TX;
+
+ return err;
+}
+
+static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
+{
+ struct intel_pt_insn intel_pt_insn;
+ uint64_t ip;
+ int err;
+
+ ip = decoder->last_ip;
+
+ while (1) {
+ err = intel_pt_walk_insn(decoder, &intel_pt_insn, ip);
+ if (err == INTEL_PT_RETURN)
+ return 0;
+ if (err == -EAGAIN) {
+ if (decoder->set_fup_tx_flags) {
+ decoder->set_fup_tx_flags = false;
+ decoder->tx_flags = decoder->fup_tx_flags;
+ decoder->state.type = INTEL_PT_TRANSACTION;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ decoder->state.flags = decoder->fup_tx_flags;
+ return 0;
+ }
+ return err;
+ }
+ decoder->set_fup_tx_flags = false;
+ if (err)
+ return err;
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_INDIRECT) {
+ intel_pt_log_at("ERROR: Unexpected indirect branch",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+ return -ENOENT;
+ }
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
+ intel_pt_log_at("ERROR: Unexpected conditional branch",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+ return -ENOENT;
+ }
+
+ intel_pt_bug(decoder);
+ }
+}
+
+static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
+{
+ struct intel_pt_insn intel_pt_insn;
+ int err;
+
+ err = intel_pt_walk_insn(decoder, &intel_pt_insn, 0);
+ if (err == INTEL_PT_RETURN)
+ return 0;
+ if (err)
+ return err;
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_INDIRECT) {
+ if (decoder->pkt_state == INTEL_PT_STATE_TIP_PGD) {
+ decoder->pge = false;
+ decoder->continuous_period = false;
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ if (decoder->packet.count != 0)
+ decoder->ip = decoder->last_ip;
+ } else {
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->state.from_ip = decoder->ip;
+ if (decoder->packet.count == 0) {
+ decoder->state.to_ip = 0;
+ } else {
+ decoder->state.to_ip = decoder->last_ip;
+ decoder->ip = decoder->last_ip;
+ }
+ }
+ return 0;
+ }
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
+ intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+ return -ENOENT;
+ }
+
+ return intel_pt_bug(decoder);
+}
+
+static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
+{
+ struct intel_pt_insn intel_pt_insn;
+ int err;
+
+ while (1) {
+ err = intel_pt_walk_insn(decoder, &intel_pt_insn, 0);
+ if (err == INTEL_PT_RETURN)
+ return 0;
+ if (err)
+ return err;
+
+ if (intel_pt_insn.op == INTEL_PT_OP_RET) {
+ if (!decoder->return_compression) {
+ intel_pt_log_at("ERROR: RET when expecting conditional branch",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ return -ENOENT;
+ }
+ if (!decoder->ret_addr) {
+ intel_pt_log_at("ERROR: Bad RET compression (stack empty)",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ return -ENOENT;
+ }
+ if (!(decoder->tnt.payload & BIT63)) {
+ intel_pt_log_at("ERROR: Bad RET compression (TNT=N)",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ return -ENOENT;
+ }
+ decoder->tnt.count -= 1;
+ if (!decoder->tnt.count)
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->tnt.payload <<= 1;
+ decoder->state.from_ip = decoder->ip;
+ decoder->ip = decoder->ret_addr;
+ decoder->state.to_ip = decoder->ip;
+ return 0;
+ }
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_INDIRECT) {
+ /* Handle deferred TIPs */
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+ if (decoder->packet.type != INTEL_PT_TIP ||
+ decoder->packet.count == 0) {
+ intel_pt_log_at("ERROR: Missing deferred TIP for indirect branch",
+ decoder->ip);
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ decoder->pkt_step = 0;
+ return -ENOENT;
+ }
+ intel_pt_set_last_ip(decoder);
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = decoder->last_ip;
+ decoder->ip = decoder->last_ip;
+ return 0;
+ }
+
+ if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
+ decoder->tnt.count -= 1;
+ if (!decoder->tnt.count)
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ if (decoder->tnt.payload & BIT63) {
+ decoder->tnt.payload <<= 1;
+ decoder->state.from_ip = decoder->ip;
+ decoder->ip += intel_pt_insn.length +
+ intel_pt_insn.rel;
+ decoder->state.to_ip = decoder->ip;
+ return 0;
+ }
+ /* Instruction sample for a non-taken branch */
+ if (decoder->state.type & INTEL_PT_INSTRUCTION) {
+ decoder->tnt.payload <<= 1;
+ decoder->state.type = INTEL_PT_INSTRUCTION;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ decoder->ip += intel_pt_insn.length;
+ return 0;
+ }
+ decoder->ip += intel_pt_insn.length;
+ if (!decoder->tnt.count)
+ return -EAGAIN;
+ decoder->tnt.payload <<= 1;
+ continue;
+ }
+
+ return intel_pt_bug(decoder);
+ }
+}
+
+static int intel_pt_mode_tsx(struct intel_pt_decoder *decoder, bool *no_tip)
+{
+ unsigned int fup_tx_flags;
+ int err;
+
+ fup_tx_flags = decoder->packet.payload &
+ (INTEL_PT_IN_TX | INTEL_PT_ABORT_TX);
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+ if (decoder->packet.type == INTEL_PT_FUP) {
+ decoder->fup_tx_flags = fup_tx_flags;
+ decoder->set_fup_tx_flags = true;
+ if (!(decoder->fup_tx_flags & INTEL_PT_ABORT_TX))
+ *no_tip = true;
+ } else {
+ intel_pt_log_at("ERROR: Missing FUP after MODE.TSX",
+ decoder->pos);
+ intel_pt_update_in_tx(decoder);
+ }
+ return 0;
+}
+
+static void intel_pt_calc_tsc_timestamp(struct intel_pt_decoder *decoder)
+{
+ uint64_t timestamp;
+
+ if (decoder->ref_timestamp) {
+ timestamp = decoder->packet.payload |
+ (decoder->ref_timestamp & (0xffULL << 56));
+ if (timestamp < decoder->ref_timestamp) {
+ if (decoder->ref_timestamp - timestamp > (1ULL << 55))
+ timestamp += (1ULL << 56);
+ } else {
+ if (timestamp - decoder->ref_timestamp > (1ULL << 55))
+ timestamp -= (1ULL << 56);
+ }
+ decoder->tsc_timestamp = timestamp;
+ decoder->timestamp = timestamp;
+ decoder->ref_timestamp = 0;
+ decoder->timestamp_insn_cnt = 0;
+ } else if (decoder->timestamp) {
+ timestamp = decoder->packet.payload |
+ (decoder->timestamp & (0xffULL << 56));
+ if (timestamp < decoder->timestamp &&
+ decoder->timestamp - timestamp < 0x100) {
+ intel_pt_log_to("ERROR: Suppressing backwards timestamp",
+ timestamp);
+ timestamp = decoder->timestamp;
+ }
+ while (timestamp < decoder->timestamp) {
+ intel_pt_log_to("Wraparound timestamp", timestamp);
+ timestamp += (1ULL << 56);
+ }
+ decoder->tsc_timestamp = timestamp;
+ decoder->timestamp = timestamp;
+ decoder->timestamp_insn_cnt = 0;
+ }
+
+ intel_pt_log_to("Setting timestamp", decoder->timestamp);
+}
+
+static int intel_pt_overflow(struct intel_pt_decoder *decoder)
+{
+ intel_pt_log("ERROR: Buffer overflow\n");
+ intel_pt_clear_tx_flags(decoder);
+ decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+ decoder->overflow = true;
+ return -EOVERFLOW;
+}
+
+/* Walk PSB+ packets when already in sync. */
+static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ while (1) {
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+
+ switch (decoder->packet.type) {
+ case INTEL_PT_PSBEND:
+ return 0;
+
+ case INTEL_PT_TIP_PGD:
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_TIP:
+ case INTEL_PT_TNT:
+ case INTEL_PT_BAD:
+ case INTEL_PT_PSB:
+ intel_pt_log("ERROR: Unexpected packet\n");
+ return -EAGAIN;
+
+ case INTEL_PT_OVF:
+ return intel_pt_overflow(decoder);
+
+ case INTEL_PT_TSC:
+ intel_pt_calc_tsc_timestamp(decoder);
+ break;
+
+ case INTEL_PT_CBR:
+ decoder->cbr = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_EXEC:
+ decoder->exec_mode = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_PIP:
+ decoder->cr3 = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_FUP:
+ decoder->pge = true;
+ break;
+
+ case INTEL_PT_MODE_TSX:
+ intel_pt_update_in_tx(decoder);
+ break;
+
+ case INTEL_PT_PAD:
+ default:
+ break;
+ }
+ }
+}
+
+static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ if (decoder->tx_flags & INTEL_PT_ABORT_TX) {
+ decoder->tx_flags = 0;
+ decoder->state.flags &= ~INTEL_PT_IN_TX;
+ decoder->state.flags |= INTEL_PT_ABORT_TX;
+ } else {
+ decoder->state.flags |= INTEL_PT_ASYNC;
+ }
+
+ while (1) {
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+
+ switch (decoder->packet.type) {
+ case INTEL_PT_TNT:
+ case INTEL_PT_FUP:
+ case INTEL_PT_PSB:
+ case INTEL_PT_TSC:
+ case INTEL_PT_CBR:
+ case INTEL_PT_MODE_TSX:
+ case INTEL_PT_BAD:
+ case INTEL_PT_PSBEND:
+ intel_pt_log("ERROR: Missing TIP after FUP\n");
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ return -ENOENT;
+
+ case INTEL_PT_OVF:
+ return intel_pt_overflow(decoder);
+
+ case INTEL_PT_TIP_PGD:
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ if (decoder->packet.count != 0) {
+ intel_pt_set_ip(decoder);
+ intel_pt_log("Omitting PGD ip " x64_fmt "\n",
+ decoder->ip);
+ }
+ decoder->pge = false;
+ decoder->continuous_period = false;
+ return 0;
+
+ case INTEL_PT_TIP_PGE:
+ decoder->pge = true;
+ intel_pt_log("Omitting PGE ip " x64_fmt "\n",
+ decoder->ip);
+ decoder->state.from_ip = 0;
+ if (decoder->packet.count == 0) {
+ decoder->state.to_ip = 0;
+ } else {
+ intel_pt_set_ip(decoder);
+ decoder->state.to_ip = decoder->ip;
+ }
+ return 0;
+
+ case INTEL_PT_TIP:
+ decoder->state.from_ip = decoder->ip;
+ if (decoder->packet.count == 0) {
+ decoder->state.to_ip = 0;
+ } else {
+ intel_pt_set_ip(decoder);
+ decoder->state.to_ip = decoder->ip;
+ }
+ return 0;
+
+ case INTEL_PT_PIP:
+ decoder->cr3 = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_EXEC:
+ decoder->exec_mode = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_PAD:
+ break;
+
+ default:
+ return intel_pt_bug(decoder);
+ }
+ }
+}
+
+static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
+{
+ bool no_tip = false;
+ int err;
+
+ while (1) {
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+next:
+ switch (decoder->packet.type) {
+ case INTEL_PT_TNT:
+ if (!decoder->packet.count)
+ break;
+ decoder->tnt = decoder->packet;
+ decoder->pkt_state = INTEL_PT_STATE_TNT;
+ err = intel_pt_walk_tnt(decoder);
+ if (err == -EAGAIN)
+ break;
+ return err;
+
+ case INTEL_PT_TIP_PGD:
+ if (decoder->packet.count != 0)
+ intel_pt_set_last_ip(decoder);
+ decoder->pkt_state = INTEL_PT_STATE_TIP_PGD;
+ return intel_pt_walk_tip(decoder);
+
+ case INTEL_PT_TIP_PGE: {
+ decoder->pge = true;
+ if (decoder->packet.count == 0) {
+ intel_pt_log_at("Skipping zero TIP.PGE",
+ decoder->pos);
+ break;
+ }
+ intel_pt_set_ip(decoder);
+ decoder->state.from_ip = 0;
+ decoder->state.to_ip = decoder->ip;
+ return 0;
+ }
+
+ case INTEL_PT_OVF:
+ return intel_pt_overflow(decoder);
+
+ case INTEL_PT_TIP:
+ if (decoder->packet.count != 0)
+ intel_pt_set_last_ip(decoder);
+ decoder->pkt_state = INTEL_PT_STATE_TIP;
+ return intel_pt_walk_tip(decoder);
+
+ case INTEL_PT_FUP:
+ if (decoder->packet.count == 0) {
+ intel_pt_log_at("Skipping zero FUP",
+ decoder->pos);
+ no_tip = false;
+ break;
+ }
+ intel_pt_set_last_ip(decoder);
+ err = intel_pt_walk_fup(decoder);
+ if (err != -EAGAIN) {
+ if (err)
+ return err;
+ if (no_tip)
+ decoder->pkt_state =
+ INTEL_PT_STATE_FUP_NO_TIP;
+ else
+ decoder->pkt_state = INTEL_PT_STATE_FUP;
+ return 0;
+ }
+ if (no_tip) {
+ no_tip = false;
+ break;
+ }
+ return intel_pt_walk_fup_tip(decoder);
+
+ case INTEL_PT_PSB:
+ intel_pt_clear_stack(&decoder->stack);
+ err = intel_pt_walk_psbend(decoder);
+ if (err == -EAGAIN)
+ goto next;
+ if (err)
+ return err;
+ break;
+
+ case INTEL_PT_PIP:
+ decoder->cr3 = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_TSC:
+ intel_pt_calc_tsc_timestamp(decoder);
+ break;
+
+ case INTEL_PT_CBR:
+ decoder->cbr = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_EXEC:
+ decoder->exec_mode = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_TSX:
+ /* MODE_TSX need not be followed by FUP */
+ if (!decoder->pge) {
+ intel_pt_update_in_tx(decoder);
+ break;
+ }
+ err = intel_pt_mode_tsx(decoder, &no_tip);
+ if (err)
+ return err;
+ goto next;
+
+ case INTEL_PT_BAD: /* Does not happen */
+ return intel_pt_bug(decoder);
+
+ case INTEL_PT_PSBEND:
+ case INTEL_PT_PAD:
+ break;
+
+ default:
+ return intel_pt_bug(decoder);
+ }
+ }
+}
+
+/* Walk PSB+ packets to get in sync. */
+static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ while (1) {
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+
+ switch (decoder->packet.type) {
+ case INTEL_PT_TIP_PGD:
+ decoder->continuous_period = false;
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_TIP:
+ intel_pt_log("ERROR: Unexpected packet\n");
+ return -ENOENT;
+
+ case INTEL_PT_FUP:
+ decoder->pge = true;
+ if (decoder->last_ip || decoder->packet.count == 6 ||
+ decoder->packet.count == 0) {
+ uint64_t current_ip = decoder->ip;
+
+ intel_pt_set_ip(decoder);
+ if (current_ip)
+ intel_pt_log_to("Setting IP",
+ decoder->ip);
+ }
+ break;
+
+ case INTEL_PT_TSC:
+ intel_pt_calc_tsc_timestamp(decoder);
+ break;
+
+ case INTEL_PT_CBR:
+ decoder->cbr = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_PIP:
+ decoder->cr3 = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_EXEC:
+ decoder->exec_mode = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_TSX:
+ intel_pt_update_in_tx(decoder);
+ break;
+
+ case INTEL_PT_TNT:
+ intel_pt_log("ERROR: Unexpected packet\n");
+ if (decoder->ip)
+ decoder->pkt_state = INTEL_PT_STATE_ERR4;
+ else
+ decoder->pkt_state = INTEL_PT_STATE_ERR3;
+ return -ENOENT;
+
+ case INTEL_PT_BAD: /* Does not happen */
+ return intel_pt_bug(decoder);
+
+ case INTEL_PT_OVF:
+ return intel_pt_overflow(decoder);
+
+ case INTEL_PT_PSBEND:
+ return 0;
+
+ case INTEL_PT_PSB:
+ case INTEL_PT_PAD:
+ default:
+ break;
+ }
+ }
+}
+
+static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ while (1) {
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+
+ switch (decoder->packet.type) {
+ case INTEL_PT_TIP_PGD:
+ decoder->continuous_period = false;
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_TIP:
+ decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
+ if (decoder->last_ip || decoder->packet.count == 6 ||
+ decoder->packet.count == 0)
+ intel_pt_set_ip(decoder);
+ if (decoder->ip)
+ return 0;
+ break;
+
+ case INTEL_PT_FUP:
+ if (decoder->overflow) {
+ if (decoder->last_ip ||
+ decoder->packet.count == 6 ||
+ decoder->packet.count == 0)
+ intel_pt_set_ip(decoder);
+ if (decoder->ip)
+ return 0;
+ }
+ if (decoder->packet.count)
+ intel_pt_set_last_ip(decoder);
+ break;
+
+ case INTEL_PT_TSC:
+ intel_pt_calc_tsc_timestamp(decoder);
+ break;
+
+ case INTEL_PT_CBR:
+ decoder->cbr = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_PIP:
+ decoder->cr3 = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_EXEC:
+ decoder->exec_mode = decoder->packet.payload;
+ break;
+
+ case INTEL_PT_MODE_TSX:
+ intel_pt_update_in_tx(decoder);
+ break;
+
+ case INTEL_PT_OVF:
+ return intel_pt_overflow(decoder);
+
+ case INTEL_PT_BAD: /* Does not happen */
+ return intel_pt_bug(decoder);
+
+ case INTEL_PT_PSB:
+ err = intel_pt_walk_psb(decoder);
+ if (err)
+ return err;
+ if (decoder->ip) {
+ /* Do not have a sample */
+ decoder->state.type = 0;
+ return 0;
+ }
+ break;
+
+ case INTEL_PT_TNT:
+ case INTEL_PT_PSBEND:
+ case INTEL_PT_PAD:
+ default:
+ break;
+ }
+ }
+}
+
+static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ intel_pt_log("Scanning for full IP\n");
+ err = intel_pt_walk_to_ip(decoder);
+ if (err)
+ return err;
+
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->overflow = false;
+
+ decoder->state.from_ip = 0;
+ decoder->state.to_ip = decoder->ip;
+ intel_pt_log_to("Setting IP", decoder->ip);
+
+ return 0;
+}
+
+static int intel_pt_part_psb(struct intel_pt_decoder *decoder)
+{
+ const unsigned char *end = decoder->buf + decoder->len;
+ size_t i;
+
+ for (i = INTEL_PT_PSB_LEN - 1; i; i--) {
+ if (i > decoder->len)
+ continue;
+ if (!memcmp(end - i, INTEL_PT_PSB_STR, i))
+ return i;
+ }
+ return 0;
+}
+
+static int intel_pt_rest_psb(struct intel_pt_decoder *decoder, int part_psb)
+{
+ size_t rest_psb = INTEL_PT_PSB_LEN - part_psb;
+ const char *psb = INTEL_PT_PSB_STR;
+
+ if (rest_psb > decoder->len ||
+ memcmp(decoder->buf, psb + part_psb, rest_psb))
+ return 0;
+
+ return rest_psb;
+}
+
+static int intel_pt_get_split_psb(struct intel_pt_decoder *decoder,
+ int part_psb)
+{
+ int rest_psb, ret;
+
+ decoder->pos += decoder->len;
+ decoder->len = 0;
+
+ ret = intel_pt_get_next_data(decoder);
+ if (ret)
+ return ret;
+
+ rest_psb = intel_pt_rest_psb(decoder, part_psb);
+ if (!rest_psb)
+ return 0;
+
+ decoder->pos -= part_psb;
+ decoder->next_buf = decoder->buf + rest_psb;
+ decoder->next_len = decoder->len - rest_psb;
+ memcpy(decoder->temp_buf, INTEL_PT_PSB_STR, INTEL_PT_PSB_LEN);
+ decoder->buf = decoder->temp_buf;
+ decoder->len = INTEL_PT_PSB_LEN;
+
+ return 0;
+}
+
+static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder)
+{
+ unsigned char *next;
+ int ret;
+
+ intel_pt_log("Scanning for PSB\n");
+ while (1) {
+ if (!decoder->len) {
+ ret = intel_pt_get_next_data(decoder);
+ if (ret)
+ return ret;
+ }
+
+ next = memmem(decoder->buf, decoder->len, INTEL_PT_PSB_STR,
+ INTEL_PT_PSB_LEN);
+ if (!next) {
+ int part_psb;
+
+ part_psb = intel_pt_part_psb(decoder);
+ if (part_psb) {
+ ret = intel_pt_get_split_psb(decoder, part_psb);
+ if (ret)
+ return ret;
+ } else {
+ decoder->pos += decoder->len;
+ decoder->len = 0;
+ }
+ continue;
+ }
+
+ decoder->pkt_step = next - decoder->buf;
+ return intel_pt_get_next_packet(decoder);
+ }
+}
+
+static int intel_pt_sync(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ decoder->pge = false;
+ decoder->continuous_period = false;
+ decoder->last_ip = 0;
+ decoder->ip = 0;
+ intel_pt_clear_stack(&decoder->stack);
+
+ err = intel_pt_scan_for_psb(decoder);
+ if (err)
+ return err;
+
+ decoder->pkt_state = INTEL_PT_STATE_NO_IP;
+
+ err = intel_pt_walk_psb(decoder);
+ if (err)
+ return err;
+
+ if (decoder->ip) {
+ decoder->state.type = 0; /* Do not have a sample */
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ } else {
+ return intel_pt_sync_ip(decoder);
+ }
+
+ return 0;
+}
+
+const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
+{
+ int err;
+
+ do {
+ decoder->state.type = INTEL_PT_BRANCH;
+ decoder->state.flags = 0;
+
+ switch (decoder->pkt_state) {
+ case INTEL_PT_STATE_NO_PSB:
+ err = intel_pt_sync(decoder);
+ break;
+ case INTEL_PT_STATE_NO_IP:
+ decoder->last_ip = 0;
+ /* Fall through */
+ case INTEL_PT_STATE_ERR_RESYNC:
+ err = intel_pt_sync_ip(decoder);
+ break;
+ case INTEL_PT_STATE_IN_SYNC:
+ err = intel_pt_walk_trace(decoder);
+ break;
+ case INTEL_PT_STATE_TNT:
+ err = intel_pt_walk_tnt(decoder);
+ if (err == -EAGAIN)
+ err = intel_pt_walk_trace(decoder);
+ break;
+ case INTEL_PT_STATE_TIP:
+ case INTEL_PT_STATE_TIP_PGD:
+ err = intel_pt_walk_tip(decoder);
+ break;
+ case INTEL_PT_STATE_FUP:
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ err = intel_pt_walk_fup(decoder);
+ if (err == -EAGAIN)
+ err = intel_pt_walk_fup_tip(decoder);
+ else if (!err)
+ decoder->pkt_state = INTEL_PT_STATE_FUP;
+ break;
+ case INTEL_PT_STATE_FUP_NO_TIP:
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ err = intel_pt_walk_fup(decoder);
+ if (err == -EAGAIN)
+ err = intel_pt_walk_trace(decoder);
+ break;
+ default:
+ err = intel_pt_bug(decoder);
+ break;
+ }
+ } while (err == -ENOLINK);
+
+ decoder->state.err = err;
+ decoder->state.timestamp = decoder->timestamp;
+ decoder->state.est_timestamp = decoder->timestamp +
+ (decoder->timestamp_insn_cnt << 1);
+ decoder->state.cr3 = decoder->cr3;
+
+ if (err)
+ decoder->state.from_ip = decoder->ip;
+
+ return &decoder->state;
+}
+
+static bool intel_pt_at_psb(unsigned char *buf, size_t len)
+{
+ if (len < INTEL_PT_PSB_LEN)
+ return false;
+ return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR,
+ INTEL_PT_PSB_LEN);
+}
+
+/**
+ * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet.
+ * @buf: pointer to buffer pointer
+ * @len: size of buffer
+ *
+ * Updates the buffer pointer to point to the start of the next PSB packet if
+ * there is one, otherwise the buffer pointer is unchanged. If @buf is updated,
+ * @len is adjusted accordingly.
+ *
+ * Return: %true if a PSB packet is found, %false otherwise.
+ */
+static bool intel_pt_next_psb(unsigned char **buf, size_t *len)
+{
+ unsigned char *next;
+
+ next = memmem(*buf, *len, INTEL_PT_PSB_STR, INTEL_PT_PSB_LEN);
+ if (next) {
+ *len -= next - *buf;
+ *buf = next;
+ return true;
+ }
+ return false;
+}
+
+/**
+ * intel_pt_step_psb - move buffer pointer to the start of the following PSB
+ * packet.
+ * @buf: pointer to buffer pointer
+ * @len: size of buffer
+ *
+ * Updates the buffer pointer to point to the start of the following PSB packet
+ * (skipping the PSB at @buf itself) if there is one, otherwise the buffer
+ * pointer is unchanged. If @buf is updated, @len is adjusted accordingly.
+ *
+ * Return: %true if a PSB packet is found, %false otherwise.
+ */
+static bool intel_pt_step_psb(unsigned char **buf, size_t *len)
+{
+ unsigned char *next;
+
+ if (!*len)
+ return false;
+
+ next = memmem(*buf + 1, *len - 1, INTEL_PT_PSB_STR, INTEL_PT_PSB_LEN);
+ if (next) {
+ *len -= next - *buf;
+ *buf = next;
+ return true;
+ }
+ return false;
+}
+
+/**
+ * intel_pt_last_psb - find the last PSB packet in a buffer.
+ * @buf: buffer
+ * @len: size of buffer
+ *
+ * This function finds the last PSB in a buffer.
+ *
+ * Return: A pointer to the last PSB in @buf if found, %NULL otherwise.
+ */
+static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
+{
+ const char *n = INTEL_PT_PSB_STR;
+ unsigned char *p;
+ size_t k;
+
+ if (len < INTEL_PT_PSB_LEN)
+ return NULL;
+
+ k = len - INTEL_PT_PSB_LEN + 1;
+ while (1) {
+ p = memrchr(buf, n[0], k);
+ if (!p)
+ return NULL;
+ if (!memcmp(p + 1, n + 1, INTEL_PT_PSB_LEN - 1))
+ return p;
+ k = p - buf;
+ if (!k)
+ return NULL;
+ }
+}
+
+/**
+ * intel_pt_next_tsc - find and return next TSC.
+ * @buf: buffer
+ * @len: size of buffer
+ * @tsc: TSC value returned
+ *
+ * Find a TSC packet in @buf and return the TSC value. This function assumes
+ * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a
+ * PSBEND packet is found.
+ *
+ * Return: %true if TSC is found, false otherwise.
+ */
+static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
+{
+ struct intel_pt_pkt packet;
+ int ret;
+
+ while (len) {
+ ret = intel_pt_get_packet(buf, len, &packet);
+ if (ret <= 0)
+ return false;
+ if (packet.type == INTEL_PT_TSC) {
+ *tsc = packet.payload;
+ return true;
+ }
+ if (packet.type == INTEL_PT_PSBEND)
+ return false;
+ buf += ret;
+ len -= ret;
+ }
+ return false;
+}
+
+/**
+ * intel_pt_tsc_cmp - compare 7-byte TSCs.
+ * @tsc1: first TSC to compare
+ * @tsc2: second TSC to compare
+ *
+ * This function compares 7-byte TSC values allowing for the possibility that
+ * TSC wrapped around. Generally it is not possible to know if TSC has wrapped
+ * around so for that purpose this function assumes the absolute difference is
+ * less than half the maximum difference.
+ *
+ * Return: %-1 if @tsc1 is before @tsc2, %0 if @tsc1 == @tsc2, %1 if @tsc1 is
+ * after @tsc2.
+ */
+static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
+{
+ const uint64_t halfway = (1ULL << 55);
+
+ if (tsc1 == tsc2)
+ return 0;
+
+ if (tsc1 < tsc2) {
+ if (tsc2 - tsc1 < halfway)
+ return -1;
+ else
+ return 1;
+ } else {
+ if (tsc1 - tsc2 < halfway)
+ return 1;
+ else
+ return -1;
+ }
+}
+
+/**
+ * intel_pt_find_overlap_tsc - determine start of non-overlapped trace data
+ * using TSC.
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ * @buf_b: second buffer
+ * @len_b: size of second buffer
+ *
+ * If the trace contains TSC we can look at the last TSC of @buf_a and the
+ * first TSC of @buf_b in order to determine if the buffers overlap, and then
+ * walk forward in @buf_b until a later TSC is found. A precondition is that
+ * @buf_a and @buf_b are positioned at a PSB.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts, or
+ * @buf_b + @len_b if there is no non-overlapped data.
+ */
+static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
+ size_t len_a,
+ unsigned char *buf_b,
+ size_t len_b)
+{
+ uint64_t tsc_a, tsc_b;
+ unsigned char *p;
+ size_t len;
+
+ p = intel_pt_last_psb(buf_a, len_a);
+ if (!p)
+ return buf_b; /* No PSB in buf_a => no overlap */
+
+ len = len_a - (p - buf_a);
+ if (!intel_pt_next_tsc(p, len, &tsc_a)) {
+ /* The last PSB+ in buf_a is incomplete, so go back one more */
+ len_a -= len;
+ p = intel_pt_last_psb(buf_a, len_a);
+ if (!p)
+ return buf_b; /* No full PSB+ => assume no overlap */
+ len = len_a - (p - buf_a);
+ if (!intel_pt_next_tsc(p, len, &tsc_a))
+ return buf_b; /* No TSC in buf_a => assume no overlap */
+ }
+
+ while (1) {
+ /* Ignore PSB+ with no TSC */
+ if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) &&
+ intel_pt_tsc_cmp(tsc_a, tsc_b) < 0)
+ return buf_b; /* tsc_a < tsc_b => no overlap */
+
+ if (!intel_pt_step_psb(&buf_b, &len_b))
+ return buf_b + len_b; /* No PSB in buf_b => no data */
+ }
+}
+
+/**
+ * intel_pt_find_overlap - determine start of non-overlapped trace data.
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ * @buf_b: second buffer
+ * @len_b: size of second buffer
+ * @have_tsc: can use TSC packets to detect overlap
+ *
+ * When trace samples or snapshots are recorded there is the possibility that
+ * the data overlaps. Note that, for the purposes of decoding, data is only
+ * useful if it begins with a PSB packet.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts, or
+ * @buf_b + @len_b if there is no non-overlapped data.
+ */
+unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
+ unsigned char *buf_b, size_t len_b,
+ bool have_tsc)
+{
+ unsigned char *found;
+
+ /* Buffer 'b' must start at PSB so throw away everything before that */
+ if (!intel_pt_next_psb(&buf_b, &len_b))
+ return buf_b + len_b; /* No PSB */
+
+ if (!intel_pt_next_psb(&buf_a, &len_a))
+ return buf_b; /* No overlap */
+
+ if (have_tsc) {
+ found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b);
+ if (found)
+ return found;
+ }
+
+ /*
+ * Buffer 'b' cannot end within buffer 'a' so, for comparison purposes,
+ * we can ignore the first part of buffer 'a'.
+ */
+ while (len_b < len_a) {
+ if (!intel_pt_step_psb(&buf_a, &len_a))
+ return buf_b; /* No overlap */
+ }
+
+ /* Now len_b >= len_a */
+ if (len_b > len_a) {
+ /* The leftover buffer 'b' must start at a PSB */
+ while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
+ if (!intel_pt_step_psb(&buf_a, &len_a))
+ return buf_b; /* No overlap */
+ }
+ }
+
+ while (1) {
+ /* Potential overlap so check the bytes */
+ found = memmem(buf_a, len_a, buf_b, len_a);
+ if (found)
+ return buf_b + len_a;
+
+ /* Try again at next PSB in buffer 'a' */
+ if (!intel_pt_step_psb(&buf_a, &len_a))
+ return buf_b; /* No overlap */
+
+ /* The leftover buffer 'b' must start at a PSB */
+ while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
+ if (!intel_pt_step_psb(&buf_a, &len_a))
+ return buf_b; /* No overlap */
+ }
+ }
+}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
new file mode 100644
index 0000000..e55615a
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -0,0 +1,89 @@
+/*
+ * intel_pt_decoder.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__INTEL_PT_DECODER_H__
+#define INCLUDE__INTEL_PT_DECODER_H__
+
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+
+#include "intel-pt-insn-decoder.h"
+
+#define INTEL_PT_IN_TX (1 << 0)
+#define INTEL_PT_ABORT_TX (1 << 1)
+#define INTEL_PT_ASYNC (1 << 2)
+
+enum intel_pt_sample_type {
+ INTEL_PT_BRANCH = 1 << 0,
+ INTEL_PT_INSTRUCTION = 1 << 1,
+ INTEL_PT_TRANSACTION = 1 << 2,
+};
+
+enum intel_pt_period_type {
+ INTEL_PT_PERIOD_NONE,
+ INTEL_PT_PERIOD_INSTRUCTIONS,
+ INTEL_PT_PERIOD_TICKS,
+};
+
+struct intel_pt_state {
+ enum intel_pt_sample_type type;
+ int err;
+ uint64_t from_ip;
+ uint64_t to_ip;
+ uint64_t cr3;
+ uint64_t timestamp;
+ uint64_t est_timestamp;
+ uint64_t trace_nr;
+ uint32_t flags;
+ enum intel_pt_insn_op insn_op;
+ int insn_len;
+};
+
+struct intel_pt_insn;
+
+struct intel_pt_buffer {
+ const unsigned char *buf;
+ size_t len;
+ bool consecutive;
+ uint64_t ref_timestamp;
+ uint64_t trace_nr;
+};
+
+struct intel_pt_params {
+ int (*get_trace)(struct intel_pt_buffer *buffer, void *data);
+ int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
+ uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
+ uint64_t max_insn_cnt, void *data);
+ void *data;
+ bool return_compression;
+ uint64_t period;
+ enum intel_pt_period_type period_type;
+};
+
+struct intel_pt_decoder;
+
+struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params);
+void intel_pt_decoder_free(struct intel_pt_decoder *decoder);
+
+const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
+
+unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
+ unsigned char *buf_b, size_t len_b,
+ bool have_tsc);
+
+const char *intel_pt_error_message(int code);
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 36/44] perf tools: Add Intel PT support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (34 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 35/44] perf tools: Add Intel PT decoder Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 37/44] perf tools: Take Intel PT into use Adrian Hunter
` (7 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add support for Intel Processor Trace.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/intel-pt.c | 2631 ++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/intel-pt.h | 35 +
3 files changed, 2667 insertions(+)
create mode 100644 tools/perf/util/intel-pt.c
create mode 100644 tools/perf/util/intel-pt.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3e790c6..944bff8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -76,6 +76,7 @@ libperf-y += cloexec.o
libperf-y += thread-stack.o
libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
+libperf-$(CONFIG_AUXTRACE) += intel-pt.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
new file mode 100644
index 0000000..1ad8cbd
--- /dev/null
+++ b/tools/perf/util/intel-pt.c
@@ -0,0 +1,2631 @@
+/*
+ * intel_pt.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../perf.h"
+#include "session.h"
+#include "machine.h"
+#include "tool.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "map.h"
+#include "cpumap.h"
+#include "color.h"
+#include "util.h"
+#include "thread.h"
+#include "thread-stack.h"
+#include "symbol.h"
+#include "callchain.h"
+#include "parse-options.h"
+#include "parse-events.h"
+#include "pmu.h"
+#include "dso.h"
+#include "debug.h"
+#include "auxtrace.h"
+#include "tsc.h"
+#include "intel-pt.h"
+
+#include "intel-pt-decoder/intel-pt-log.h"
+#include "intel-pt-decoder/intel-pt-decoder.h"
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
+#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+#define INTEL_PT_DEFAULT_SAMPLE_SIZE KiB(4)
+
+#define INTEL_PT_MAX_SAMPLE_SIZE KiB(60)
+
+#define INTEL_PT_PSB_PERIOD_NEAR 256
+
+struct intel_pt_snapshot_ref {
+ void *ref_buf;
+ size_t ref_offset;
+ bool wrapped;
+};
+
+struct intel_pt_recording {
+ struct auxtrace_record itr;
+ struct perf_pmu *intel_pt_pmu;
+ int have_sched_switch;
+ struct perf_evlist *evlist;
+ bool snapshot_mode;
+ bool snapshot_init_done;
+ size_t snapshot_size;
+ size_t snapshot_ref_buf_size;
+ int snapshot_ref_cnt;
+ struct intel_pt_snapshot_ref *snapshot_refs;
+};
+
+struct intel_pt {
+ struct auxtrace auxtrace;
+ struct auxtrace_queues queues;
+ struct auxtrace_heap heap;
+ u32 auxtrace_type;
+ struct perf_session *session;
+ struct machine *machine;
+ struct perf_evsel *switch_evsel;
+ struct thread *unknown_thread;
+ bool timeless_decoding;
+ bool sampling_mode;
+ bool snapshot_mode;
+ bool per_cpu_mmaps;
+ bool have_tsc;
+ bool data_queued;
+ bool est_tsc;
+ bool sync_switch;
+ bool est_tsc_orig;
+ int have_sched_switch;
+ u32 pmu_type;
+ u64 kernel_start;
+ u64 switch_ip;
+ u64 ptss_ip;
+
+ struct perf_tsc_conversion tc;
+ bool cap_user_time_zero;
+
+ struct itrace_synth_opts synth_opts;
+
+ bool sample_instructions;
+ u64 instructions_sample_type;
+ u64 instructions_sample_period;
+ u64 instructions_id;
+
+ bool sample_branches;
+ u32 branches_filter;
+ u64 branches_sample_type;
+ u64 branches_id;
+
+ bool sample_transactions;
+ u64 transactions_sample_type;
+ u64 transactions_id;
+
+ bool synth_needs_swap;
+
+ u64 tsc_bit;
+ u64 noretcomp_bit;
+};
+
+enum switch_state {
+ INTEL_PT_SS_NOT_TRACING,
+ INTEL_PT_SS_UNKNOWN,
+ INTEL_PT_SS_TRACING,
+ INTEL_PT_SS_EXPECTING_SWITCH_EVENT,
+ INTEL_PT_SS_EXPECTING_SWITCH_IP,
+};
+
+struct intel_pt_queue {
+ struct intel_pt *pt;
+ unsigned int queue_nr;
+ struct auxtrace_buffer *buffer;
+ void *decoder;
+ const struct intel_pt_state *state;
+ struct ip_callchain *chain;
+ union perf_event *event_buf;
+ bool on_heap;
+ bool stop;
+ bool step_through_buffers;
+ bool use_buffer_pid_tid;
+ pid_t pid, tid;
+ int cpu;
+ int switch_state;
+ pid_t next_tid;
+ struct thread *thread;
+ bool exclude_kernel;
+ bool have_sample;
+ u64 time;
+ u64 timestamp;
+ u32 flags;
+ u16 insn_len;
+};
+
+static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
+ unsigned char *buf, size_t len)
+{
+ struct intel_pt_pkt packet;
+ size_t pos = 0;
+ int ret, pkt_len, i;
+ char desc[INTEL_PT_PKT_DESC_MAX];
+ const char *color = PERF_COLOR_BLUE;
+
+ color_fprintf(stdout, color,
+ ". ... Intel Processor Trace data: size %zu bytes\n",
+ len);
+
+ while (len) {
+ ret = intel_pt_get_packet(buf, len, &packet);
+ if (ret > 0)
+ pkt_len = ret;
+ else
+ pkt_len = 1;
+ printf(".");
+ color_fprintf(stdout, color, " %08x: ", pos);
+ for (i = 0; i < pkt_len; i++)
+ color_fprintf(stdout, color, " %02x", buf[i]);
+ for (; i < 16; i++)
+ color_fprintf(stdout, color, " ");
+ if (ret > 0) {
+ ret = intel_pt_pkt_desc(&packet, desc,
+ INTEL_PT_PKT_DESC_MAX);
+ if (ret > 0)
+ color_fprintf(stdout, color, " %s\n", desc);
+ } else {
+ color_fprintf(stdout, color, " Bad packet!\n");
+ }
+ pos += pkt_len;
+ buf += pkt_len;
+ len -= pkt_len;
+ }
+}
+
+static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
+ size_t len)
+{
+ printf(".\n");
+ intel_pt_dump(pt, buf, len);
+}
+
+static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
+ struct auxtrace_buffer *b)
+{
+ void *start;
+
+ start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
+ pt->have_tsc);
+ if (!start)
+ return -EINVAL;
+ b->use_size = b->data + b->size - start;
+ b->use_data = start;
+ return 0;
+}
+
+static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq,
+ struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (queue->cpu == -1 && buffer->cpu != -1)
+ ptq->cpu = buffer->cpu;
+
+ ptq->pid = buffer->pid;
+ ptq->tid = buffer->tid;
+
+ intel_pt_log("queue %u cpu %d pid %d tid %d\n",
+ ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+
+ ptq->thread = NULL;
+
+ if (ptq->tid != -1) {
+ if (ptq->pid != -1)
+ ptq->thread = machine__findnew_thread(ptq->pt->machine,
+ ptq->pid,
+ ptq->tid);
+ else
+ ptq->thread = machine__find_thread(ptq->pt->machine, -1,
+ ptq->tid);
+ }
+}
+
+/* This function assumes data is processed sequentially only */
+static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+{
+ struct intel_pt_queue *ptq = data;
+ struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer;
+ struct auxtrace_queue *queue;
+
+ if (ptq->stop) {
+ b->len = 0;
+ return 0;
+ }
+
+ queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+ buffer = auxtrace_buffer__next(queue, buffer);
+ if (!buffer) {
+ if (old_buffer)
+ auxtrace_buffer__drop_data(old_buffer);
+ b->len = 0;
+ return 0;
+ }
+
+ ptq->buffer = buffer;
+
+ if (!buffer->data) {
+ int fd = perf_data_file__fd(ptq->pt->session->file);
+
+ buffer->data = auxtrace_buffer__get_data(buffer, fd);
+ if (!buffer->data)
+ return -ENOMEM;
+ }
+
+ if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer &&
+ intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
+ return -ENOMEM;
+
+ if (old_buffer)
+ auxtrace_buffer__drop_data(old_buffer);
+
+ if (buffer->use_data) {
+ b->len = buffer->use_size;
+ b->buf = buffer->use_data;
+ } else {
+ b->len = buffer->size;
+ b->buf = buffer->data;
+ }
+ b->ref_timestamp = buffer->reference;
+
+ if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
+ !buffer->consecutive)) {
+ b->consecutive = false;
+ b->trace_nr = buffer->buffer_nr;
+ } else {
+ b->consecutive = true;
+ }
+
+ if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid ||
+ ptq->tid != buffer->tid))
+ intel_pt_use_buffer_pid_tid(ptq, queue, buffer);
+
+ if (ptq->step_through_buffers)
+ ptq->stop = true;
+
+ if (!b->len)
+ return intel_pt_get_trace(b, data);
+
+ return 0;
+}
+
+struct intel_pt_cache_entry {
+ struct auxtrace_cache_entry entry;
+ u64 insn_cnt;
+ u64 byte_cnt;
+ enum intel_pt_insn_op op;
+ enum intel_pt_insn_branch branch;
+ int length;
+ int32_t rel;
+};
+
+static int intel_pt_config_div(const char *var, const char *value, void *data)
+{
+ int *div = data;
+ long val;
+
+ if (!strcmp(var, "intel-pt.cache-divisor")) {
+ val = strtol(value, NULL, 0);
+ if (val > 0 && val <= INT_MAX)
+ *div = val;
+ }
+
+ return 0;
+}
+
+static int intel_pt_cache_divisor(void)
+{
+ static int div;
+
+ if (div)
+ return div;
+
+ perf_config(intel_pt_config_div, &div);
+
+ if (!div)
+ div = 64;
+
+ return div;
+}
+
+static unsigned int intel_pt_cache_size(struct dso *dso,
+ struct machine *machine)
+{
+ off_t size;
+
+ size = dso__data_size(dso, machine);
+ size /= intel_pt_cache_divisor();
+ if (size < 1000)
+ return 10;
+ if (size > (1 << 21))
+ return 21;
+ return 32 - __builtin_clz(size);
+}
+
+static struct auxtrace_cache *intel_pt_cache(struct dso *dso,
+ struct machine *machine)
+{
+ struct auxtrace_cache *c;
+ unsigned int bits;
+
+ if (dso->auxtrace_cache)
+ return dso->auxtrace_cache;
+
+ bits = intel_pt_cache_size(dso, machine);
+
+ /* Ignoring cache creation failure */
+ c = auxtrace_cache__new(bits, sizeof(struct intel_pt_cache_entry), 200);
+
+ dso->auxtrace_cache = c;
+
+ return c;
+}
+
+static int intel_pt_cache_add(struct dso *dso, struct machine *machine,
+ u64 offset, u64 insn_cnt, u64 byte_cnt,
+ struct intel_pt_insn *intel_pt_insn)
+{
+ struct auxtrace_cache *c = intel_pt_cache(dso, machine);
+ struct intel_pt_cache_entry *e;
+ int err;
+
+ if (!c)
+ return -ENOMEM;
+
+ e = auxtrace_cache__alloc_entry(c);
+ if (!e)
+ return -ENOMEM;
+
+ e->insn_cnt = insn_cnt;
+ e->byte_cnt = byte_cnt;
+ e->op = intel_pt_insn->op;
+ e->branch = intel_pt_insn->branch;
+ e->length = intel_pt_insn->length;
+ e->rel = intel_pt_insn->rel;
+
+ err = auxtrace_cache__add(c, offset, &e->entry);
+ if (err)
+ auxtrace_cache__free_entry(c, e);
+
+ return err;
+}
+
+static struct intel_pt_cache_entry *
+intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
+{
+ struct auxtrace_cache *c = intel_pt_cache(dso, machine);
+
+ if (!c)
+ return NULL;
+
+ return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
+}
+
+static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
+ uint64_t *insn_cnt_ptr, uint64_t *ip,
+ uint64_t to_ip, uint64_t max_insn_cnt,
+ void *data)
+{
+ struct intel_pt_queue *ptq = data;
+ struct machine *machine = ptq->pt->machine;
+ struct thread *thread;
+ struct addr_location al;
+ unsigned char buf[1024];
+ size_t bufsz;
+ ssize_t len;
+ int x86_64;
+ u8 cpumode;
+ u64 offset, start_offset, start_ip;
+ u64 insn_cnt = 0;
+ bool one_map = true;
+
+ if (to_ip && *ip == to_ip)
+ goto out_no_cache;
+
+ bufsz = intel_pt_insn_max_size();
+
+ if (*ip >= ptq->pt->kernel_start)
+ cpumode = PERF_RECORD_MISC_KERNEL;
+ else
+ cpumode = PERF_RECORD_MISC_USER;
+
+ thread = ptq->thread;
+ if (!thread) {
+ if (cpumode != PERF_RECORD_MISC_KERNEL)
+ return -EINVAL;
+ thread = ptq->pt->unknown_thread;
+ }
+
+ while (1) {
+ thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
+ if (!al.map || !al.map->dso)
+ return -EINVAL;
+
+ if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
+ dso__data_status_seen(al.map->dso,
+ DSO_DATA_STATUS_SEEN_ITRACE))
+ return -ENOENT;
+
+ offset = al.map->map_ip(al.map, *ip);
+
+ if (!to_ip && one_map) {
+ struct intel_pt_cache_entry *e;
+
+ e = intel_pt_cache_lookup(al.map->dso, machine, offset);
+ if (e &&
+ (!max_insn_cnt || e->insn_cnt <= max_insn_cnt)) {
+ *insn_cnt_ptr = e->insn_cnt;
+ *ip += e->byte_cnt;
+ intel_pt_insn->op = e->op;
+ intel_pt_insn->branch = e->branch;
+ intel_pt_insn->length = e->length;
+ intel_pt_insn->rel = e->rel;
+ intel_pt_log_insn_no_data(intel_pt_insn, *ip);
+ return 0;
+ }
+ }
+
+ start_offset = offset;
+ start_ip = *ip;
+
+ /* Load maps to ensure dso->is_64_bit has been updated */
+ map__load(al.map, machine->symbol_filter);
+
+ x86_64 = al.map->dso->is_64_bit;
+
+ while (1) {
+ len = dso__data_read_offset(al.map->dso, machine,
+ offset, buf, bufsz);
+ if (len <= 0)
+ return -EINVAL;
+
+ if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn))
+ return -EINVAL;
+
+ intel_pt_log_insn(intel_pt_insn, *ip);
+
+ insn_cnt += 1;
+
+ if (intel_pt_insn->branch != INTEL_PT_BR_NO_BRANCH)
+ goto out;
+
+ if (max_insn_cnt && insn_cnt >= max_insn_cnt)
+ goto out_no_cache;
+
+ *ip += intel_pt_insn->length;
+
+ if (to_ip && *ip == to_ip)
+ goto out_no_cache;
+
+ if (*ip >= al.map->end)
+ break;
+
+ offset += intel_pt_insn->length;
+ }
+ one_map = false;
+ }
+out:
+ *insn_cnt_ptr = insn_cnt;
+
+ if (!one_map)
+ goto out_no_cache;
+
+ /*
+ * Didn't lookup in the 'to_ip' case, so do it now to prevent duplicate
+ * entries.
+ */
+ if (to_ip) {
+ struct intel_pt_cache_entry *e;
+
+ e = intel_pt_cache_lookup(al.map->dso, machine, start_offset);
+ if (e)
+ return 0;
+ }
+
+ /* Ignore cache errors */
+ intel_pt_cache_add(al.map->dso, machine, start_offset, insn_cnt,
+ *ip - start_ip, intel_pt_insn);
+
+ return 0;
+
+out_no_cache:
+ *insn_cnt_ptr = insn_cnt;
+ return 0;
+}
+
+static bool intel_pt_get_config(struct intel_pt *pt,
+ struct perf_event_attr *attr, u64 *config)
+{
+ if (attr->type == pt->pmu_type) {
+ if (config)
+ *config = attr->config;
+ return true;
+ }
+
+ return false;
+}
+
+static bool intel_pt_exclude_kernel(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
+ !evsel->attr.exclude_kernel)
+ return false;
+ }
+ return true;
+}
+
+static bool intel_pt_return_compression(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+ u64 config;
+
+ if (!pt->noretcomp_bit)
+ return true;
+
+ evlist__for_each(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+ (config & pt->noretcomp_bit))
+ return false;
+ }
+ return true;
+}
+
+static bool intel_pt_timeless_decoding(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+ bool timeless_decoding = true;
+ u64 config;
+
+ if (!pt->tsc_bit || !pt->cap_user_time_zero)
+ return true;
+
+ evlist__for_each(pt->session->evlist, evsel) {
+ if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
+ return true;
+ if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+ if (config & pt->tsc_bit)
+ timeless_decoding = false;
+ else
+ return true;
+ }
+ }
+ return timeless_decoding;
+}
+
+static bool intel_pt_tracing_kernel(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
+ !evsel->attr.exclude_kernel)
+ return true;
+ }
+ return false;
+}
+
+static bool intel_pt_have_tsc(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+ bool have_tsc = false;
+ u64 config;
+
+ if (!pt->tsc_bit)
+ return false;
+
+ evlist__for_each(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+ if (config & pt->tsc_bit)
+ have_tsc = true;
+ else
+ return false;
+ }
+ }
+ return have_tsc;
+}
+
+static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
+{
+ u64 quot, rem;
+
+ quot = ns / pt->tc.time_mult;
+ rem = ns % pt->tc.time_mult;
+ return (quot << pt->tc.time_shift) + (rem << pt->tc.time_shift) /
+ pt->tc.time_mult;
+}
+
+static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
+ unsigned int queue_nr)
+{
+ struct intel_pt_params params = {0};
+ struct intel_pt_queue *ptq;
+
+ ptq = zalloc(sizeof(struct intel_pt_queue));
+ if (!ptq)
+ return NULL;
+
+ if (pt->synth_opts.callchain) {
+ size_t sz = sizeof(struct ip_callchain);
+
+ sz += pt->synth_opts.callchain_sz * sizeof(u64);
+ ptq->chain = zalloc(sz);
+ if (!ptq->chain)
+ goto out_free;
+ }
+
+ ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+ if (!ptq->event_buf)
+ goto out_free;
+
+ ptq->pt = pt;
+ ptq->queue_nr = queue_nr;
+ ptq->exclude_kernel = intel_pt_exclude_kernel(pt);
+ ptq->pid = -1;
+ ptq->tid = -1;
+ ptq->cpu = -1;
+ ptq->next_tid = -1;
+
+ params.get_trace = intel_pt_get_trace;
+ params.walk_insn = intel_pt_walk_next_insn;
+ params.data = ptq;
+ params.return_compression = intel_pt_return_compression(pt);
+
+ if (pt->synth_opts.instructions) {
+ if (pt->synth_opts.period) {
+ switch (pt->synth_opts.period_type) {
+ case PERF_ITRACE_PERIOD_INSTRUCTIONS:
+ params.period_type =
+ INTEL_PT_PERIOD_INSTRUCTIONS;
+ params.period = pt->synth_opts.period;
+ break;
+ case PERF_ITRACE_PERIOD_TICKS:
+ params.period_type = INTEL_PT_PERIOD_TICKS;
+ params.period = pt->synth_opts.period;
+ break;
+ case PERF_ITRACE_PERIOD_NANOSECS:
+ params.period_type = INTEL_PT_PERIOD_TICKS;
+ params.period = intel_pt_ns_to_ticks(pt,
+ pt->synth_opts.period);
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (!params.period) {
+ params.period_type = INTEL_PT_PERIOD_INSTRUCTIONS;
+ params.period = 1000;
+ }
+ }
+
+ ptq->decoder = intel_pt_decoder_new(¶ms);
+ if (!ptq->decoder)
+ goto out_free;
+
+ return ptq;
+
+out_free:
+ zfree(&ptq->event_buf);
+ zfree(&ptq->chain);
+ free(ptq);
+ return NULL;
+}
+
+static void intel_pt_free_queue(void *priv)
+{
+ struct intel_pt_queue *ptq = priv;
+
+ if (!ptq)
+ return;
+ intel_pt_decoder_free(ptq->decoder);
+ zfree(&ptq->event_buf);
+ zfree(&ptq->chain);
+ free(ptq);
+}
+
+static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
+ struct auxtrace_queue *queue)
+{
+ struct intel_pt_queue *ptq = queue->priv;
+
+ if (queue->tid == -1 || pt->have_sched_switch) {
+ ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu);
+ ptq->thread = NULL;
+ }
+
+ if (!ptq->thread && ptq->tid != -1)
+ ptq->thread = machine__find_thread(pt->machine, -1, ptq->tid);
+
+ if (ptq->thread) {
+ ptq->pid = ptq->thread->pid_;
+ if (queue->cpu == -1)
+ ptq->cpu = ptq->thread->cpu;
+ }
+}
+
+static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
+{
+ if (ptq->state->flags & INTEL_PT_ABORT_TX) {
+ ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
+ } else if (ptq->state->flags & INTEL_PT_ASYNC) {
+ if (ptq->state->to_ip)
+ ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+ PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_INTERRUPT;
+ else
+ ptq->flags = PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_TRACE_END;
+ ptq->insn_len = 0;
+ } else {
+ if (ptq->state->from_ip)
+ ptq->flags = intel_pt_insn_type(ptq->state->insn_op);
+ else
+ ptq->flags = PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_TRACE_BEGIN;
+ if (ptq->state->flags & INTEL_PT_IN_TX)
+ ptq->flags |= PERF_IP_FLAG_IN_TX;
+ ptq->insn_len = ptq->state->insn_len;
+ }
+}
+
+static int intel_pt_setup_queue(struct intel_pt *pt, struct auxtrace_queue *queue,
+ unsigned int queue_nr)
+{
+ struct intel_pt_queue *ptq = queue->priv;
+
+ if (list_empty(&queue->head))
+ return 0;
+
+ if (!ptq) {
+ ptq = intel_pt_alloc_queue(pt, queue_nr);
+ if (!ptq)
+ return -ENOMEM;
+ queue->priv = ptq;
+
+ if (queue->cpu != -1)
+ ptq->cpu = queue->cpu;
+ ptq->tid = queue->tid;
+
+ if (pt->sampling_mode) {
+ if (pt->timeless_decoding)
+ ptq->step_through_buffers = true;
+ if (pt->timeless_decoding || !pt->have_sched_switch)
+ ptq->use_buffer_pid_tid = true;
+ }
+ }
+
+ if (!ptq->on_heap &&
+ (!pt->sync_switch ||
+ ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
+ const struct intel_pt_state *state;
+ int ret;
+
+ if (pt->timeless_decoding)
+ return 0;
+
+ intel_pt_log("queue %u getting timestamp\n", queue_nr);
+ intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
+ queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+ while (1) {
+ state = intel_pt_decode(ptq->decoder);
+ if (state->err) {
+ if (state->err == -ENODATA) {
+ intel_pt_log("queue %u has no timestamp\n",
+ queue_nr);
+ return 0;
+ }
+ continue;
+ }
+ if (state->timestamp)
+ break;
+ }
+
+ ptq->timestamp = state->timestamp;
+ intel_pt_log("queue %u timestamp 0x%" PRIx64 "\n",
+ queue_nr, ptq->timestamp);
+ ptq->state = state;
+ ptq->have_sample = true;
+ intel_pt_sample_flags(ptq);
+ ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
+ if (ret)
+ return ret;
+ ptq->on_heap = true;
+ }
+
+ return 0;
+}
+
+static int intel_pt_setup_queues(struct intel_pt *pt)
+{
+ unsigned int i;
+ int ret;
+
+ for (i = 0; i < pt->queues.nr_queues; i++) {
+ ret = intel_pt_setup_queue(pt, &pt->queues.queue_array[i], i);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static int intel_pt_inject_event(union perf_event *event,
+ struct perf_sample *sample, u64 type,
+ bool swapped)
+{
+ event->header.size = perf_event__sample_event_size(sample, type, 0);
+ return perf_event__synthesize_sample(event, type, 0, sample, swapped);
+}
+
+static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
+{
+ int ret;
+ struct intel_pt *pt = ptq->pt;
+ union perf_event *event = ptq->event_buf;
+ struct perf_sample sample = {0};
+
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.misc = PERF_RECORD_MISC_USER;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ if (!pt->timeless_decoding)
+ sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+ sample.ip = ptq->state->from_ip;
+ sample.pid = ptq->pid;
+ sample.tid = ptq->tid;
+ sample.addr = ptq->state->to_ip;
+ sample.id = ptq->pt->branches_id;
+ sample.stream_id = ptq->pt->branches_id;
+ sample.period = 1;
+ sample.cpu = ptq->cpu;
+
+ if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
+ return 0;
+
+ if (pt->synth_opts.inject) {
+ ret = intel_pt_inject_event(event, &sample,
+ pt->branches_sample_type,
+ pt->synth_needs_swap);
+ if (ret)
+ return ret;
+ }
+
+ ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+ if (ret)
+ pr_err("Intel Processor Trace: failed to deliver branch event, error %d\n",
+ ret);
+
+ return ret;
+}
+
+static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
+{
+ int ret;
+ struct intel_pt *pt = ptq->pt;
+ union perf_event *event = ptq->event_buf;
+ struct perf_sample sample = {0};
+
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.misc = PERF_RECORD_MISC_USER;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ if (!pt->timeless_decoding)
+ sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+ sample.ip = ptq->state->from_ip;
+ sample.pid = ptq->pid;
+ sample.tid = ptq->tid;
+ sample.addr = ptq->state->to_ip;
+ sample.id = ptq->pt->instructions_id;
+ sample.stream_id = ptq->pt->instructions_id;
+ sample.period = ptq->pt->instructions_sample_period;
+ sample.cpu = ptq->cpu;
+
+ if (pt->synth_opts.callchain) {
+ thread_stack__sample(ptq->thread, ptq->chain,
+ pt->synth_opts.callchain_sz, sample.ip);
+ sample.callchain = ptq->chain;
+ }
+
+ if (pt->synth_opts.inject) {
+ ret = intel_pt_inject_event(event, &sample,
+ pt->instructions_sample_type,
+ pt->synth_needs_swap);
+ if (ret)
+ return ret;
+ }
+
+ ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+ if (ret)
+ pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n",
+ ret);
+
+ return ret;
+}
+
+static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
+{
+ int ret;
+ struct intel_pt *pt = ptq->pt;
+ union perf_event *event = ptq->event_buf;
+ struct perf_sample sample = {0};
+
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.misc = PERF_RECORD_MISC_USER;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ if (!pt->timeless_decoding)
+ sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+ sample.ip = ptq->state->from_ip;
+ sample.pid = ptq->pid;
+ sample.tid = ptq->tid;
+ sample.addr = ptq->state->to_ip;
+ sample.id = ptq->pt->transactions_id;
+ sample.stream_id = ptq->pt->transactions_id;
+ sample.period = 1;
+ sample.cpu = ptq->cpu;
+ sample.flags = ptq->flags;
+ sample.insn_len = ptq->insn_len;
+
+ if (pt->synth_opts.callchain) {
+ thread_stack__sample(ptq->thread, ptq->chain,
+ pt->synth_opts.callchain_sz, sample.ip);
+ sample.callchain = ptq->chain;
+ }
+
+ if (pt->synth_opts.inject) {
+ ret = intel_pt_inject_event(event, &sample,
+ pt->transactions_sample_type,
+ pt->synth_needs_swap);
+ if (ret)
+ return ret;
+ }
+
+ ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+ if (ret)
+ pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
+ ret);
+
+ return ret;
+}
+
+static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
+ pid_t pid, pid_t tid, u64 ip)
+{
+ union perf_event event;
+ const char *msg;
+ int err;
+
+ msg = intel_pt_error_message(code);
+
+ auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE , code,
+ cpu, pid, tid, ip, msg);
+
+ err = perf_session__deliver_synth_event(pt->session, &event, NULL);
+ if (err)
+ pr_err("Intel Processor Trace: failed to deliver error event, error %d\n",
+ err);
+
+ return err;
+}
+
+static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
+{
+ struct auxtrace_queue *queue;
+ pid_t tid = ptq->next_tid;
+ int err;
+
+ if (tid == -1)
+ return 0;
+
+ intel_pt_log("switch: cpu %d tid %d\n", ptq->cpu, tid);
+
+ err = machine__set_current_tid(pt->machine, ptq->cpu, -1, tid);
+
+ queue = &pt->queues.queue_array[ptq->queue_nr];
+ intel_pt_set_pid_tid_cpu(pt, queue);
+
+ ptq->next_tid = -1;
+
+ return err;
+}
+
+static int intel_pt_sample(struct intel_pt_queue *ptq)
+{
+ const struct intel_pt_state *state = ptq->state;
+ struct intel_pt *pt = ptq->pt;
+ int err;
+
+ if (!ptq->have_sample)
+ return 0;
+
+ ptq->have_sample = false;
+
+ if (pt->sample_instructions &&
+ (state->type & INTEL_PT_INSTRUCTION)) {
+ err = intel_pt_synth_instruction_sample(ptq);
+ if (err)
+ return err;
+ }
+
+ if (pt->sample_transactions &&
+ (state->type & INTEL_PT_TRANSACTION)) {
+ err = intel_pt_synth_transaction_sample(ptq);
+ if (err)
+ return err;
+ }
+
+ if (!(state->type & INTEL_PT_BRANCH))
+ return 0;
+
+ if (pt->synth_opts.callchain)
+ thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
+ state->to_ip, ptq->insn_len,
+ state->trace_nr);
+
+ if (pt->sample_branches) {
+ err = intel_pt_synth_branch_sample(ptq);
+ if (err)
+ return err;
+ }
+
+ if (!pt->sync_switch)
+ return 0;
+
+ if (state->to_ip == pt->switch_ip &&
+ (ptq->flags & PERF_IP_FLAG_CALL)) {
+ switch (ptq->switch_state) {
+ case INTEL_PT_SS_UNKNOWN:
+ case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+ err = intel_pt_next_tid(pt, ptq);
+ if (err)
+ return err;
+ ptq->switch_state = INTEL_PT_SS_TRACING;
+ break;
+ default:
+ ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_EVENT;
+ return 1;
+ }
+ } else if (!state->to_ip) {
+ ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
+ } else if (ptq->switch_state == INTEL_PT_SS_NOT_TRACING) {
+ ptq->switch_state = INTEL_PT_SS_UNKNOWN;
+ } else if (ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
+ state->to_ip == pt->ptss_ip &&
+ (ptq->flags & PERF_IP_FLAG_CALL)) {
+ ptq->switch_state = INTEL_PT_SS_TRACING;
+ }
+
+ return 0;
+}
+
+static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
+{
+ struct map *map;
+ struct symbol *sym, *start;
+ u64 ip, switch_ip = 0;
+
+ if (ptss_ip)
+ *ptss_ip = 0;
+
+ map = machine__kernel_map(machine, MAP__FUNCTION);
+ if (!map)
+ return 0;
+
+ if (map__load(map, machine->symbol_filter))
+ return 0;
+
+ start = dso__first_symbol(map->dso, MAP__FUNCTION);
+
+ for (sym = start; sym; sym = dso__next_symbol(sym)) {
+ if (sym->binding == STB_GLOBAL &&
+ !strcmp(sym->name, "__switch_to")) {
+ ip = map->unmap_ip(map, sym->start);
+ if (ip >= map->start && ip < map->end) {
+ switch_ip = ip;
+ break;
+ }
+ }
+ }
+
+ if (!switch_ip || !ptss_ip)
+ return 0;
+
+ for (sym = start; sym; sym = dso__next_symbol(sym)) {
+ if (!strcmp(sym->name, "perf_trace_sched_switch")) {
+ ip = map->unmap_ip(map, sym->start);
+ if (ip >= map->start && ip < map->end) {
+ *ptss_ip = ip;
+ break;
+ }
+ }
+ }
+
+ return switch_ip;
+}
+
+static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
+{
+ const struct intel_pt_state *state = ptq->state;
+ struct intel_pt *pt = ptq->pt;
+ int err;
+
+ if (!pt->kernel_start) {
+ pt->kernel_start = machine__kernel_start(pt->machine);
+ if (pt->per_cpu_mmaps && pt->have_sched_switch &&
+ !pt->timeless_decoding && intel_pt_tracing_kernel(pt) &&
+ !pt->sampling_mode) {
+ pt->switch_ip = intel_pt_switch_ip(pt->machine,
+ &pt->ptss_ip);
+ if (pt->switch_ip) {
+ intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
+ pt->switch_ip, pt->ptss_ip);
+ pt->sync_switch = true;
+ pt->est_tsc_orig = pt->est_tsc;
+ pt->est_tsc = false;
+ }
+ }
+ }
+
+ intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
+ ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+ while (1) {
+ err = intel_pt_sample(ptq);
+ if (err)
+ return err;
+
+ state = intel_pt_decode(ptq->decoder);
+ if (state->err) {
+ if (state->err == -ENODATA)
+ return 1;
+ if (pt->sync_switch &&
+ state->from_ip >= pt->kernel_start) {
+ pt->sync_switch = false;
+ pt->est_tsc = pt->est_tsc_orig;
+ intel_pt_next_tid(pt, ptq);
+ }
+ if (pt->synth_opts.errors) {
+ err = intel_pt_synth_error(pt, -state->err,
+ ptq->cpu, ptq->pid,
+ ptq->tid,
+ state->from_ip);
+ if (err)
+ return err;
+ }
+ continue;
+ }
+
+ ptq->state = state;
+ ptq->have_sample = true;
+ intel_pt_sample_flags(ptq);
+
+ /* Use estimated TSC upon return to user space */
+ if (pt->est_tsc) {
+ if (state->from_ip >= pt->kernel_start &&
+ state->to_ip &&
+ state->to_ip < pt->kernel_start)
+ ptq->timestamp = state->est_timestamp;
+ else if (state->timestamp > ptq->timestamp)
+ ptq->timestamp = state->timestamp;
+ /* Use estimated TSC in unknown switch state */
+ } else if (pt->sync_switch &&
+ ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
+ state->to_ip == pt->switch_ip &&
+ (ptq->flags & PERF_IP_FLAG_CALL) &&
+ ptq->next_tid == -1) {
+ ptq->timestamp = state->est_timestamp;
+ } else if (state->timestamp > ptq->timestamp) {
+ ptq->timestamp = state->timestamp;
+ }
+
+ if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
+ *timestamp = ptq->timestamp;
+ return 0;
+ }
+ }
+ return 0;
+}
+
+static inline int intel_pt_update_queues(struct intel_pt *pt)
+{
+ if (pt->queues.new_data) {
+ pt->queues.new_data = false;
+ return intel_pt_setup_queues(pt);
+ }
+ return 0;
+}
+
+static int intel_pt_process_queues(struct intel_pt *pt, u64 timestamp)
+{
+ unsigned int queue_nr;
+ u64 ts;
+ int ret;
+
+ while (1) {
+ struct auxtrace_queue *queue;
+ struct intel_pt_queue *ptq;
+
+ if (!pt->heap.heap_cnt)
+ return 0;
+
+ if (pt->heap.heap_array[0].ordinal >= timestamp)
+ return 0;
+
+ queue_nr = pt->heap.heap_array[0].queue_nr;
+ queue = &pt->queues.queue_array[queue_nr];
+ ptq = queue->priv;
+
+ intel_pt_log("queue %u processing 0x%" PRIx64 " to 0x%" PRIx64 "\n",
+ queue_nr, pt->heap.heap_array[0].ordinal,
+ timestamp);
+
+ auxtrace_heap__pop(&pt->heap);
+
+ if (pt->heap.heap_cnt) {
+ ts = pt->heap.heap_array[0].ordinal + 1;
+ if (ts > timestamp)
+ ts = timestamp;
+ } else {
+ ts = timestamp;
+ }
+
+ intel_pt_set_pid_tid_cpu(pt, queue);
+
+ ret = intel_pt_run_decoder(ptq, &ts);
+
+ if (ret < 0) {
+ auxtrace_heap__add(&pt->heap, queue_nr, ts);
+ return ret;
+ }
+
+ if (!ret) {
+ ret = auxtrace_heap__add(&pt->heap, queue_nr, ts);
+ if (ret < 0)
+ return ret;
+ } else {
+ ptq->on_heap = false;
+ }
+ }
+
+ return 0;
+}
+
+static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid,
+ u64 time_)
+{
+ struct auxtrace_queues *queues = &pt->queues;
+ unsigned int i;
+ u64 ts = 0;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+ struct intel_pt_queue *ptq = queue->priv;
+
+ if (ptq && (tid == -1 || ptq->tid == tid)) {
+ ptq->time = time_;
+ intel_pt_set_pid_tid_cpu(pt, queue);
+ intel_pt_run_decoder(ptq, &ts);
+ }
+ }
+ return 0;
+}
+
+static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
+{
+ union perf_event event;
+ int err;
+
+ auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE ,
+ ENOSPC, sample->cpu, sample->pid, sample->tid, 0,
+ "Lost trace data");
+
+ err = perf_session__deliver_synth_event(pt->session, &event, NULL);
+ if (err)
+ pr_err("Intel Processor Trace: failed to deliver error event, error %d\n",
+ err);
+
+ return err;
+}
+
+static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
+{
+ unsigned i, j;
+
+ if (cpu < 0 || !pt->queues.nr_queues)
+ return NULL;
+
+ if ((unsigned)cpu >= pt->queues.nr_queues)
+ i = pt->queues.nr_queues - 1;
+ else
+ i = cpu;
+
+ if (pt->queues.queue_array[i].cpu == cpu)
+ return pt->queues.queue_array[i].priv;
+
+ for (j = 0; i > 0; j++) {
+ if (pt->queues.queue_array[--i].cpu == cpu)
+ return pt->queues.queue_array[i].priv;
+ }
+
+ for (; j < pt->queues.nr_queues; j++) {
+ if (pt->queues.queue_array[j].cpu == cpu)
+ return pt->queues.queue_array[j].priv;
+ }
+
+ return NULL;
+}
+
+static int intel_pt_process_switch(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct intel_pt_queue *ptq;
+ struct perf_evsel *evsel;
+ pid_t tid;
+ int cpu, err;
+
+ evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
+ if (evsel != pt->switch_evsel)
+ return 0;
+
+ tid = perf_evsel__intval(evsel, sample, "next_pid");
+ cpu = sample->cpu;
+
+ intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+ cpu, tid, sample->time, perf_time_to_tsc(sample->time,
+ &pt->tc));
+
+ if (!pt->sync_switch)
+ goto out;
+
+ ptq = intel_pt_cpu_to_ptq(pt, cpu);
+ if (!ptq)
+ goto out;
+
+ switch (ptq->switch_state) {
+ case INTEL_PT_SS_NOT_TRACING:
+ ptq->next_tid = -1;
+ break;
+ case INTEL_PT_SS_UNKNOWN:
+ case INTEL_PT_SS_TRACING:
+ ptq->next_tid = tid;
+ ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_IP;
+ return 0;
+ case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
+ if (!ptq->on_heap) {
+ ptq->timestamp = perf_time_to_tsc(sample->time,
+ &pt->tc);
+ err = auxtrace_heap__add(&pt->heap, ptq->queue_nr,
+ ptq->timestamp);
+ if (err)
+ return err;
+ ptq->on_heap = true;
+ }
+ ptq->switch_state = INTEL_PT_SS_TRACING;
+ break;
+ case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+ ptq->next_tid = tid;
+ intel_pt_log("ERROR: cpu %d expecting switch ip\n", cpu);
+ break;
+ default:
+ break;
+ }
+out:
+ return machine__set_current_tid(pt->machine, cpu, -1, tid);
+}
+
+static int intel_pt_process_itrace_start(struct intel_pt *pt,
+ union perf_event *event,
+ struct perf_sample *sample)
+{
+ if (!pt->per_cpu_mmaps)
+ return 0;
+
+ intel_pt_log("itrace_start: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+ sample->cpu, event->itrace_start.pid,
+ event->itrace_start.tid, sample->time,
+ perf_time_to_tsc(sample->time, &pt->tc));
+
+ return machine__set_current_tid(pt->machine, sample->cpu,
+ event->itrace_start.pid,
+ event->itrace_start.tid);
+}
+
+static int intel_pt_process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+ u64 timestamp;
+ int err = 0;
+
+ if (dump_trace)
+ return 0;
+
+ if (!tool->ordered_events) {
+ pr_err("Intel Processor Trace requires ordered events\n");
+ return -EINVAL;
+ }
+
+ if (sample->time)
+ timestamp = perf_time_to_tsc(sample->time, &pt->tc);
+ else
+ timestamp = 0;
+
+ if (timestamp || pt->timeless_decoding) {
+ err = intel_pt_update_queues(pt);
+ if (err)
+ return err;
+ }
+
+ if (pt->timeless_decoding) {
+ if (event->header.type == PERF_RECORD_EXIT) {
+ err = intel_pt_process_timeless_queues(pt,
+ event->comm.tid,
+ sample->time);
+ }
+ } else if (timestamp) {
+ err = intel_pt_process_queues(pt, timestamp);
+ }
+ if (err)
+ return err;
+
+ if (event->header.type == PERF_RECORD_AUX &&
+ (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
+ pt->synth_opts.errors)
+ err = intel_pt_lost(pt, sample);
+
+ if (pt->switch_evsel && event->header.type == PERF_RECORD_SAMPLE)
+ err = intel_pt_process_switch(pt, sample);
+ else if (event->header.type == PERF_RECORD_ITRACE_START)
+ err = intel_pt_process_itrace_start(pt, event, sample);
+
+ return err;
+}
+
+static int intel_pt_flush(struct perf_session *session, struct perf_tool *tool)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+ int ret;
+
+ if (dump_trace)
+ return 0;
+
+ if (!tool->ordered_events)
+ return -EINVAL;
+
+ ret = intel_pt_update_queues(pt);
+ if (ret < 0)
+ return ret;
+
+ if (pt->timeless_decoding)
+ return intel_pt_process_timeless_queues(pt, -1,
+ MAX_TIMESTAMP - 1);
+
+ return intel_pt_process_queues(pt, MAX_TIMESTAMP);
+}
+
+static void intel_pt_free_events(struct perf_session *session)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+ struct auxtrace_queues *queues = &pt->queues;
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ intel_pt_free_queue(queues->queue_array[i].priv);
+ queues->queue_array[i].priv = NULL;
+ }
+ intel_pt_log_disable();
+ auxtrace_queues__free(queues);
+}
+
+static void intel_pt_free(struct perf_session *session)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+
+ auxtrace_heap__free(&pt->heap);
+ intel_pt_free_events(session);
+ session->auxtrace = NULL;
+ thread__delete(pt->unknown_thread);
+ free(pt);
+}
+
+static int intel_pt_process_auxtrace_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool __maybe_unused)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+
+ if (pt->sampling_mode)
+ return 0;
+
+ if (!pt->data_queued) {
+ struct auxtrace_buffer *buffer;
+ off_t data_offset;
+ int fd = perf_data_file__fd(session->file);
+ int err;
+
+ if (perf_data_file__is_pipe(session->file)) {
+ data_offset = 0;
+ } else {
+ data_offset = lseek(fd, 0, SEEK_CUR);
+ if (data_offset == -1)
+ return -errno;
+ }
+
+ err = auxtrace_queues__add_event(&pt->queues, session, event,
+ data_offset, &buffer);
+ if (err)
+ return err;
+
+ /* Dump here now we have copied a piped trace out of the pipe */
+ if (dump_trace) {
+ if (auxtrace_buffer__get_data(buffer, fd)) {
+ intel_pt_dump_event(pt, buffer->data,
+ buffer->size);
+ auxtrace_buffer__put_data(buffer);
+ }
+ }
+ }
+
+ return 0;
+}
+
+struct intel_pt_synth {
+ struct perf_tool dummy_tool;
+ struct perf_session *session;
+};
+
+static int intel_pt_event_synth(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+ struct intel_pt_synth *intel_pt_synth =
+ container_of(tool, struct intel_pt_synth, dummy_tool);
+
+ return perf_session__deliver_synth_event(intel_pt_synth->session, event,
+ NULL);
+}
+
+static int intel_pt_synth_event(struct perf_session *session,
+ struct perf_event_attr *attr, u64 id)
+{
+ struct intel_pt_synth intel_pt_synth;
+
+ memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth));
+ intel_pt_synth.session = session;
+
+ return perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1,
+ &id, intel_pt_event_synth);
+}
+
+static int intel_pt_synth_events(struct intel_pt *pt,
+ struct perf_session *session)
+{
+ struct perf_evlist *evlist = session->evlist;
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr;
+ bool found = false;
+ u64 id;
+ int err;
+
+ evlist__for_each(evlist, evsel) {
+ if (evsel->attr.type == pt->pmu_type && evsel->ids) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ pr_debug("There are no selected events with Intel Processor Trace data\n");
+ return 0;
+ }
+
+ memset(&attr, 0, sizeof(struct perf_event_attr));
+ attr.size = sizeof(struct perf_event_attr);
+ attr.type = PERF_TYPE_HARDWARE;
+ attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+ attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+ PERF_SAMPLE_PERIOD;
+ if (pt->timeless_decoding)
+ attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+ else
+ attr.sample_type |= PERF_SAMPLE_TIME;
+ if (!pt->per_cpu_mmaps)
+ attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
+ attr.exclude_user = evsel->attr.exclude_user;
+ attr.exclude_kernel = evsel->attr.exclude_kernel;
+ attr.exclude_hv = evsel->attr.exclude_hv;
+ attr.exclude_host = evsel->attr.exclude_host;
+ attr.exclude_guest = evsel->attr.exclude_guest;
+ attr.sample_id_all = evsel->attr.sample_id_all;
+ attr.read_format = evsel->attr.read_format;
+
+ id = evsel->id[0] + 1000000000;
+ if (!id)
+ id = 1;
+
+ if (pt->synth_opts.instructions) {
+ attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+ if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS)
+ attr.sample_period =
+ intel_pt_ns_to_ticks(pt, pt->synth_opts.period);
+ else
+ attr.sample_period = pt->synth_opts.period;
+ pt->instructions_sample_period = attr.sample_period;
+ if (pt->synth_opts.callchain)
+ attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+ pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+ id, (u64)attr.sample_type);
+ err = intel_pt_synth_event(session, &attr, id);
+ if (err) {
+ pr_err("%s: failed to synthesize 'instructions' event type\n",
+ __func__);
+ return err;
+ }
+ pt->sample_instructions = true;
+ pt->instructions_sample_type = attr.sample_type;
+ pt->instructions_id = id;
+ id += 1;
+ }
+
+ if (pt->synth_opts.transactions) {
+ attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+ attr.sample_period = 1;
+ if (pt->synth_opts.callchain)
+ attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+ pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+ id, (u64)attr.sample_type);
+ err = intel_pt_synth_event(session, &attr, id);
+ if (err) {
+ pr_err("%s: failed to synthesize 'transactions' event type\n",
+ __func__);
+ return err;
+ }
+ pt->sample_transactions = true;
+ pt->transactions_id = id;
+ id += 1;
+ evlist__for_each(evlist, evsel) {
+ if (evsel->id && evsel->id[0] == pt->transactions_id) {
+ if (evsel->name)
+ zfree(&evsel->name);
+ evsel->name = strdup("transactions");
+ break;
+ }
+ }
+ }
+
+ if (pt->synth_opts.branches) {
+ attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+ attr.sample_period = 1;
+ attr.sample_type |= PERF_SAMPLE_ADDR;
+ attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN;
+ pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+ id, (u64)attr.sample_type);
+ err = intel_pt_synth_event(session, &attr, id);
+ if (err) {
+ pr_err("%s: failed to synthesize 'branches' event type\n",
+ __func__);
+ return err;
+ }
+ pt->sample_branches = true;
+ pt->branches_sample_type = attr.sample_type;
+ pt->branches_id = id;
+ }
+
+ pt->synth_needs_swap = evsel->needs_swap;
+
+ return 0;
+}
+
+static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each_reverse(evlist, evsel) {
+ const char *name = perf_evsel__name(evsel);
+
+ if (!strcmp(name, "sched:sched_switch"))
+ return evsel;
+ }
+
+ return NULL;
+}
+
+enum {
+ INTEL_PT_PMU_TYPE,
+ INTEL_PT_TIME_SHIFT,
+ INTEL_PT_TIME_MULT,
+ INTEL_PT_TIME_ZERO,
+ INTEL_PT_CAP_USER_TIME_ZERO,
+ INTEL_PT_TSC_BIT,
+ INTEL_PT_NORETCOMP_BIT,
+ INTEL_PT_HAVE_SCHED_SWITCH,
+ INTEL_PT_SNAPSHOT_MODE,
+ INTEL_PT_PER_CPU_MMAPS,
+ INTEL_PT_AUXTRACE_PRIV_SIZE,
+};
+
+static const char * const intel_pt_info_fmts[] = {
+ [INTEL_PT_PMU_TYPE] = " PMU Type %"PRId64"\n",
+ [INTEL_PT_TIME_SHIFT] = " Time Shift %"PRIu64"\n",
+ [INTEL_PT_TIME_MULT] = " Time Muliplier %"PRIu64"\n",
+ [INTEL_PT_TIME_ZERO] = " Time Zero %"PRIu64"\n",
+ [INTEL_PT_CAP_USER_TIME_ZERO] = " Cap Time Zero %"PRId64"\n",
+ [INTEL_PT_TSC_BIT] = " TSC bit %#"PRIx64"\n",
+ [INTEL_PT_NORETCOMP_BIT] = " NoRETComp bit %#"PRIx64"\n",
+ [INTEL_PT_HAVE_SCHED_SWITCH] = " Have sched_switch %"PRId64"\n",
+ [INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n",
+ [INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n",
+};
+
+static void intel_pt_print_info(u64 *arr, int start, int finish)
+{
+ int i;
+
+ if (!dump_trace)
+ return;
+
+ for (i = start; i <= finish; i++)
+ fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
+}
+
+u64 intel_pt_auxtrace_info_priv[INTEL_PT_AUXTRACE_PRIV_SIZE];
+
+int intel_pt_process_auxtrace_info(union perf_event *event,
+ struct perf_session *session)
+{
+ struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+ size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
+ struct intel_pt *pt;
+ int err;
+
+ if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+ min_sz)
+ return -EINVAL;
+
+ pt = zalloc(sizeof(struct intel_pt));
+ if (!pt)
+ return -ENOMEM;
+
+ err = auxtrace_queues__init(&pt->queues);
+ if (err)
+ goto err_free;
+
+ intel_pt_log_set_name(INTEL_PT_PMU_NAME);
+
+ pt->session = session;
+ pt->machine = &session->machines.host; /* No kvm support */
+ pt->auxtrace_type = auxtrace_info->type;
+ pt->pmu_type = auxtrace_info->priv[INTEL_PT_PMU_TYPE];
+ pt->tc.time_shift = auxtrace_info->priv[INTEL_PT_TIME_SHIFT];
+ pt->tc.time_mult = auxtrace_info->priv[INTEL_PT_TIME_MULT];
+ pt->tc.time_zero = auxtrace_info->priv[INTEL_PT_TIME_ZERO];
+ pt->cap_user_time_zero = auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO];
+ pt->tsc_bit = auxtrace_info->priv[INTEL_PT_TSC_BIT];
+ pt->noretcomp_bit = auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT];
+ pt->have_sched_switch = auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH];
+ pt->snapshot_mode = auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE];
+ pt->per_cpu_mmaps = auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS];
+ intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_PMU_TYPE,
+ INTEL_PT_PER_CPU_MMAPS);
+
+ pt->timeless_decoding = intel_pt_timeless_decoding(pt);
+ pt->have_tsc = intel_pt_have_tsc(pt);
+ pt->sampling_mode = false;
+ pt->est_tsc = pt->per_cpu_mmaps && !pt->timeless_decoding;
+
+ pt->unknown_thread = thread__new(999999999, 999999999);
+ if (!pt->unknown_thread) {
+ err = -ENOMEM;
+ goto err_free_queues;
+ }
+ err = thread__set_comm(pt->unknown_thread, "unknown", 0);
+ if (err)
+ goto err_delete_thread;
+ if (thread__init_map_groups(pt->unknown_thread, pt->machine)) {
+ err = -ENOMEM;
+ goto err_delete_thread;
+ }
+
+ pt->auxtrace.process_event = intel_pt_process_event;
+ pt->auxtrace.process_auxtrace_event = intel_pt_process_auxtrace_event;
+ pt->auxtrace.flush_events = intel_pt_flush;
+ pt->auxtrace.free_events = intel_pt_free_events;
+ pt->auxtrace.free = intel_pt_free;
+ session->auxtrace = &pt->auxtrace;
+
+ if (dump_trace)
+ return 0;
+
+ if (pt->have_sched_switch == 1) {
+ pt->switch_evsel = intel_pt_find_sched_switch(session->evlist);
+ if (!pt->switch_evsel) {
+ pr_err("%s: missing sched_switch event\n", __func__);
+ goto err_delete_thread;
+ }
+ }
+
+ if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+ pt->synth_opts = *session->itrace_synth_opts;
+ } else {
+ itrace_synth_opts__set_default(&pt->synth_opts);
+ if (use_browser != -1) {
+ pt->synth_opts.branches = false;
+ pt->synth_opts.callchain = true;
+ }
+ }
+
+ if (pt->synth_opts.log)
+ intel_pt_log_enable();
+
+ if (pt->synth_opts.calls)
+ pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_TRACE_END;
+ if (pt->synth_opts.returns)
+ pt->branches_filter |= PERF_IP_FLAG_RETURN |
+ PERF_IP_FLAG_TRACE_BEGIN;
+
+ if (pt->synth_opts.callchain && !symbol_conf.use_callchain) {
+ symbol_conf.use_callchain = true;
+ if (callchain_register_param(&callchain_param) < 0) {
+ symbol_conf.use_callchain = false;
+ pt->synth_opts.callchain = false;
+ }
+ }
+
+ err = intel_pt_synth_events(pt, session);
+ if (err)
+ goto err_delete_thread;
+
+ err = auxtrace_queues__process_index(&pt->queues, session);
+ if (err)
+ goto err_delete_thread;
+
+ if (pt->queues.populated)
+ pt->data_queued = true;
+
+ if (pt->timeless_decoding)
+ pr_debug2("Intel PT decoding without timestamps\n");
+
+ return 0;
+
+err_delete_thread:
+ thread__delete(pt->unknown_thread);
+err_free_queues:
+ intel_pt_log_disable();
+ auxtrace_queues__free(&pt->queues);
+ session->auxtrace = NULL;
+err_free:
+ free(pt);
+ return err;
+}
+
+static int intel_pt_parse_terms_with_default(struct list_head *formats,
+ const char *str,
+ u64 *config)
+{
+ struct list_head *terms;
+ struct perf_event_attr attr = {0};
+ int err;
+
+ terms = malloc(sizeof(struct list_head));
+ if (!terms)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(terms);
+
+ err = parse_events_terms(terms, str);
+ if (err)
+ goto out_free;
+
+ attr.config = *config;
+ err = perf_pmu__config_terms(formats, &attr, terms, true);
+ if (err)
+ goto out_free;
+
+ *config = attr.config;
+out_free:
+ parse_events__free_terms(terms);
+ return err;
+}
+
+static int intel_pt_parse_terms(struct list_head *formats, const char *str,
+ u64 *config)
+{
+ *config = 0;
+ return intel_pt_parse_terms_with_default(formats, str, config);
+}
+
+static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ return 256;
+}
+
+static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
+{
+ u64 config;
+
+ intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &config);
+ return config;
+}
+
+static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ unsigned long long snapshot_size = 0;
+ char *endptr;
+
+ if (str) {
+ snapshot_size = strtoull(str, &endptr, 0);
+ if (*endptr || snapshot_size > SIZE_MAX)
+ return -1;
+ }
+
+ opts->auxtrace_snapshot_mode = true;
+ opts->auxtrace_snapshot_size = snapshot_size;
+
+ ptr->snapshot_size = snapshot_size;
+
+ return 0;
+}
+
+struct perf_event_attr *
+intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
+{
+ struct perf_event_attr *attr;
+
+ attr = zalloc(sizeof(struct perf_event_attr));
+ if (!attr)
+ return NULL;
+
+ attr->config = intel_pt_default_config(intel_pt_pmu);
+
+ intel_pt_pmu->selectable = true;
+
+ return attr;
+}
+
+static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+{
+ return sizeof(intel_pt_auxtrace_info_priv);
+}
+
+static int intel_pt_info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
+ struct perf_event_mmap_page *pc;
+ struct perf_tsc_conversion tc = {0};
+ bool cap_user_time_zero = false, per_cpu_mmaps;
+ u64 tsc_bit, noretcomp_bit;
+ int err;
+
+ if (priv_size != sizeof(intel_pt_auxtrace_info_priv))
+ return -EINVAL;
+
+ intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
+ intel_pt_parse_terms(&intel_pt_pmu->format, "noretcomp",
+ &noretcomp_bit);
+
+ if (!session->evlist->nr_mmaps)
+ return -EINVAL;
+
+ pc = session->evlist->mmap[0].base;
+ if (pc) {
+ err = perf_read_tsc_conversion(pc, &tc);
+ if (err) {
+ if (err != -EOPNOTSUPP)
+ return err;
+ } else {
+ cap_user_time_zero = tc.time_mult != 0;
+ }
+ if (!cap_user_time_zero)
+ ui__warning("Intel Processor Trace: TSC not available\n");
+ }
+
+ per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus);
+
+ auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
+ auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
+ auxtrace_info->priv[INTEL_PT_TIME_SHIFT] = tc.time_shift;
+ auxtrace_info->priv[INTEL_PT_TIME_MULT] = tc.time_mult;
+ auxtrace_info->priv[INTEL_PT_TIME_ZERO] = tc.time_zero;
+ auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+ auxtrace_info->priv[INTEL_PT_TSC_BIT] = tsc_bit;
+ auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT] = noretcomp_bit;
+ auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH] = ptr->have_sched_switch;
+ auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE] = ptr->snapshot_mode;
+ auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS] = per_cpu_mmaps;
+
+ return 0;
+}
+
+static int intel_pt_track_switches(struct perf_evlist *evlist)
+{
+ const char *sched_switch = "sched:sched_switch";
+ struct perf_evsel *evsel;
+ int err;
+
+ if (!perf_evlist__can_select_event(evlist, sched_switch))
+ return -EPERM;
+
+ err = parse_events(evlist, sched_switch);
+ if (err) {
+ pr_debug2("%s: failed to parse %s, error %d\n",
+ __func__, sched_switch, err);
+ return err;
+ }
+
+ evsel = perf_evlist__last(evlist);
+
+ perf_evsel__set_sample_bit(evsel, CPU);
+ perf_evsel__set_sample_bit(evsel, TIME);
+
+ evsel->system_wide = true;
+ evsel->no_aux_samples = true;
+ evsel->immediate = true;
+
+ return 0;
+}
+
+static int intel_pt_recording_options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
+ bool have_timing_info;
+ struct perf_evsel *evsel, *intel_pt_evsel = NULL;
+ const struct cpu_map *cpus = evlist->cpus;
+ bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+ u64 tsc_bit;
+
+ ptr->evlist = evlist;
+ ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+ evlist__for_each(evlist, evsel) {
+ if (evsel->attr.type == intel_pt_pmu->type) {
+ if (intel_pt_evsel) {
+ pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n");
+ return -EINVAL;
+ }
+ evsel->attr.freq = 0;
+ evsel->attr.sample_period = 1;
+ intel_pt_evsel = evsel;
+ opts->full_auxtrace = true;
+ }
+ }
+
+ if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+ pr_err("Snapshot mode (-S option) requires " INTEL_PT_PMU_NAME " PMU event (-e " INTEL_PT_PMU_NAME ")\n");
+ return -EINVAL;
+ }
+
+ if (opts->use_clockid) {
+ pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n");
+ return -EINVAL;
+ }
+
+ if (!opts->full_auxtrace)
+ return 0;
+
+ /* Set default sizes for snapshot mode */
+ if (opts->auxtrace_snapshot_mode) {
+ size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist);
+
+ if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+ if (privileged) {
+ opts->auxtrace_mmap_pages = MiB(4) / page_size;
+ } else {
+ opts->auxtrace_mmap_pages = KiB(128) / page_size;
+ if (opts->mmap_pages == UINT_MAX)
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ } else if (!opts->auxtrace_mmap_pages && !privileged &&
+ opts->mmap_pages == UINT_MAX) {
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ if (!opts->auxtrace_snapshot_size)
+ opts->auxtrace_snapshot_size =
+ opts->auxtrace_mmap_pages * (size_t)page_size;
+ if (!opts->auxtrace_mmap_pages) {
+ size_t sz = opts->auxtrace_snapshot_size;
+
+ sz = round_up(sz, page_size) / page_size;
+ opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+ }
+ if (opts->auxtrace_snapshot_size >
+ opts->auxtrace_mmap_pages * (size_t)page_size) {
+ pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+ opts->auxtrace_snapshot_size,
+ opts->auxtrace_mmap_pages * (size_t)page_size);
+ return -EINVAL;
+ }
+ if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+ pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+ return -EINVAL;
+ }
+ pr_debug2("Intel PT snapshot size: %zu\n",
+ opts->auxtrace_snapshot_size);
+ if (psb_period &&
+ opts->auxtrace_snapshot_size <= psb_period +
+ INTEL_PT_PSB_PERIOD_NEAR)
+ ui__warning("Intel PT snapshot size (%zu) may be too small for PSB period (%zu)\n",
+ opts->auxtrace_snapshot_size, psb_period);
+ }
+
+ /* Set default sizes for full trace mode */
+ if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+ if (privileged) {
+ opts->auxtrace_mmap_pages = MiB(4) / page_size;
+ } else {
+ opts->auxtrace_mmap_pages = KiB(128) / page_size;
+ if (opts->mmap_pages == UINT_MAX)
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ }
+
+ /* Validate auxtrace_mmap_pages */
+ if (opts->auxtrace_mmap_pages) {
+ size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+ size_t min_sz;
+
+ if (opts->auxtrace_snapshot_mode)
+ min_sz = KiB(4);
+ else
+ min_sz = KiB(8);
+
+ if (sz < min_sz || !is_power_of_2(sz)) {
+ pr_err("Invalid mmap size for Intel Processor Trace: must be at least %zuKiB and a power of 2\n",
+ min_sz / 1024);
+ return -EINVAL;
+ }
+ }
+
+ intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
+
+ if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit))
+ have_timing_info = true;
+ else
+ have_timing_info = false;
+
+ /*
+ * Per-cpu recording needs sched_switch events to distinguish different
+ * threads.
+ */
+ if (have_timing_info && !cpu_map__empty(cpus)) {
+ int err;
+
+ err = intel_pt_track_switches(evlist);
+ if (err == -EPERM)
+ pr_debug2("Unable to select sched:sched_switch\n");
+ else if (err)
+ return err;
+ else
+ ptr->have_sched_switch = 1;
+ }
+
+ 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);
+ /*
+ * In the case of per-cpu mmaps, we need the CPU on the
+ * AUX event.
+ */
+ if (!cpu_map__empty(cpus))
+ perf_evsel__set_sample_bit(intel_pt_evsel, CPU);
+ }
+
+ /* Add dummy event to keep tracking */
+ if (opts->full_auxtrace) {
+ struct perf_evsel *tracking_evsel;
+ int err;
+
+ err = parse_events(evlist, "dummy:u");
+ if (err)
+ return err;
+
+ tracking_evsel = perf_evlist__last(evlist);
+
+ perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+ tracking_evsel->attr.freq = 0;
+ tracking_evsel->attr.sample_period = 1;
+
+ /* In per-cpu case, always need the time of mmap events etc */
+ if (!cpu_map__empty(cpus))
+ perf_evsel__set_sample_bit(tracking_evsel, TIME);
+ }
+
+ /*
+ * Warn the user when we do not have enough information to decode i.e.
+ * per-cpu with no sched_switch (except workload-only).
+ */
+ if (!ptr->have_sched_switch && !cpu_map__empty(cpus) &&
+ !target__none(&opts->target))
+ ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
+
+ return 0;
+}
+
+static int intel_pt_snapshot_start(struct auxtrace_record *itr)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(ptr->evlist, evsel) {
+ if (evsel->attr.type == ptr->intel_pt_pmu->type)
+ return perf_evlist__disable_event(ptr->evlist, evsel);
+ }
+ return -EINVAL;
+}
+
+static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(ptr->evlist, evsel) {
+ if (evsel->attr.type == ptr->intel_pt_pmu->type)
+ return perf_evlist__enable_event(ptr->evlist, evsel);
+ }
+ return -EINVAL;
+}
+
+static int intel_pt_alloc_snapshot_refs(struct intel_pt_recording *ptr, int idx)
+{
+ const size_t sz = sizeof(struct intel_pt_snapshot_ref);
+ int cnt = ptr->snapshot_ref_cnt, new_cnt = cnt * 2;
+ struct intel_pt_snapshot_ref *refs;
+
+ if (!new_cnt)
+ new_cnt = 16;
+
+ while (new_cnt <= idx)
+ new_cnt *= 2;
+
+ refs = calloc(new_cnt, sz);
+ if (!refs)
+ return -ENOMEM;
+
+ memcpy(refs, ptr->snapshot_refs, cnt * sz);
+
+ ptr->snapshot_refs = refs;
+ ptr->snapshot_ref_cnt = new_cnt;
+
+ return 0;
+}
+
+static void intel_pt_free_snapshot_refs(struct intel_pt_recording *ptr)
+{
+ int i;
+
+ for (i = 0; i < ptr->snapshot_ref_cnt; i++)
+ free(ptr->snapshot_refs[i].ref_buf);
+ free(ptr->snapshot_refs);
+}
+
+static void intel_pt_recording_free(struct auxtrace_record *itr)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+
+ intel_pt_free_snapshot_refs(ptr);
+ free(ptr);
+}
+
+static int intel_pt_alloc_snapshot_ref(struct intel_pt_recording *ptr, int idx,
+ size_t snapshot_buf_size)
+{
+ size_t ref_buf_size = ptr->snapshot_ref_buf_size;
+ void *ref_buf;
+
+ ref_buf = zalloc(ref_buf_size);
+ if (!ref_buf)
+ return -ENOMEM;
+
+ ptr->snapshot_refs[idx].ref_buf = ref_buf;
+ ptr->snapshot_refs[idx].ref_offset = snapshot_buf_size - ref_buf_size;
+
+ return 0;
+}
+
+static size_t intel_pt_snapshot_ref_buf_size(struct intel_pt_recording *ptr,
+ size_t snapshot_buf_size)
+{
+ const size_t max_size = 256 * 1024;
+ size_t buf_size = 0, psb_period;
+
+ if (ptr->snapshot_size <= 64 * 1024)
+ return 0;
+
+ psb_period = intel_pt_psb_period(ptr->intel_pt_pmu, ptr->evlist);
+ if (psb_period)
+ buf_size = psb_period * 2;
+
+ if (!buf_size || buf_size > max_size)
+ buf_size = max_size;
+
+ if (buf_size >= snapshot_buf_size)
+ return 0;
+
+ if (buf_size >= ptr->snapshot_size / 2)
+ return 0;
+
+ return buf_size;
+}
+
+static int intel_pt_snapshot_init(struct intel_pt_recording *ptr,
+ size_t snapshot_buf_size)
+{
+ if (ptr->snapshot_init_done)
+ return 0;
+
+ ptr->snapshot_init_done = true;
+
+ ptr->snapshot_ref_buf_size = intel_pt_snapshot_ref_buf_size(ptr,
+ snapshot_buf_size);
+
+ return 0;
+}
+
+/**
+ * intel_pt_compare_buffers - compare bytes in a buffer to a circular buffer.
+ * @buf1: first buffer
+ * @compare_size: number of bytes to compare
+ * @buf2: second buffer (a circular buffer)
+ * @offs2: offset in second buffer
+ * @buf2_size: size of second buffer
+ *
+ * The comparison allows for the possibility that the bytes to compare in the
+ * circular buffer are not contiguous. It is assumed that @compare_size <=
+ * @buf2_size. This function returns %false if the bytes are identical, %true
+ * otherwise.
+ */
+static bool intel_pt_compare_buffers(void *buf1, size_t compare_size,
+ void *buf2, size_t offs2, size_t buf2_size)
+{
+ size_t end2 = offs2 + compare_size, part_size;
+
+ if (end2 <= buf2_size)
+ return memcmp(buf1, buf2 + offs2, compare_size);
+
+ part_size = end2 - buf2_size;
+ if (memcmp(buf1, buf2 + offs2, part_size))
+ return true;
+
+ compare_size -= part_size;
+
+ return memcmp(buf1 + part_size, buf2, compare_size);
+}
+
+static bool intel_pt_compare_ref(void *ref_buf, size_t ref_offset,
+ size_t ref_size, size_t buf_size,
+ void *data, size_t head)
+{
+ size_t ref_end = ref_offset + ref_size;
+
+ if (ref_end > buf_size) {
+ if (head > ref_offset || head < ref_end - buf_size)
+ return true;
+ } else if (head > ref_offset && head < ref_end) {
+ return true;
+ }
+
+ return intel_pt_compare_buffers(ref_buf, ref_size, data, ref_offset,
+ buf_size);
+}
+
+static void intel_pt_copy_ref(void *ref_buf, size_t ref_size, size_t buf_size,
+ void *data, size_t head)
+{
+ if (head >= ref_size) {
+ memcpy(ref_buf, data + head - ref_size, ref_size);
+ } else {
+ memcpy(ref_buf, data, head);
+ ref_size -= head;
+ memcpy(ref_buf + head, data + buf_size - ref_size, ref_size);
+ }
+}
+
+static bool intel_pt_wrapped(struct intel_pt_recording *ptr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 head)
+{
+ struct intel_pt_snapshot_ref *ref = &ptr->snapshot_refs[idx];
+ bool wrapped;
+
+ wrapped = intel_pt_compare_ref(ref->ref_buf, ref->ref_offset,
+ ptr->snapshot_ref_buf_size, mm->len,
+ data, head);
+
+ intel_pt_copy_ref(ref->ref_buf, ptr->snapshot_ref_buf_size, mm->len,
+ data, head);
+
+ return wrapped;
+}
+
+static bool intel_pt_first_wrap(u64 *data, size_t buf_size)
+{
+ int i, a, b;
+
+ b = buf_size >> 3;
+ a = b - 512;
+ if (a < 0)
+ a = 0;
+
+ for (i = a; i < b; i++) {
+ if (data[i])
+ return true;
+ }
+
+ return false;
+}
+
+static int intel_pt_find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 *head, u64 *old)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ bool wrapped;
+ int err;
+
+ pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+ __func__, idx, (size_t)*old, (size_t)*head);
+
+ err = intel_pt_snapshot_init(ptr, mm->len);
+ if (err)
+ goto out_err;
+
+ if (idx >= ptr->snapshot_ref_cnt) {
+ err = intel_pt_alloc_snapshot_refs(ptr, idx);
+ if (err)
+ goto out_err;
+ }
+
+ if (ptr->snapshot_ref_buf_size) {
+ if (!ptr->snapshot_refs[idx].ref_buf) {
+ err = intel_pt_alloc_snapshot_ref(ptr, idx, mm->len);
+ if (err)
+ goto out_err;
+ }
+ wrapped = intel_pt_wrapped(ptr, idx, mm, data, *head);
+ } else {
+ wrapped = ptr->snapshot_refs[idx].wrapped;
+ if (!wrapped && intel_pt_first_wrap((u64 *)data, mm->len)) {
+ ptr->snapshot_refs[idx].wrapped = true;
+ wrapped = true;
+ }
+ }
+
+ /*
+ * In full trace mode 'head' continually increases. However in snapshot
+ * mode 'head' is an offset within the buffer. Here 'old' and 'head'
+ * are adjusted to match the full trace case which expects that 'old' is
+ * always less than 'head'.
+ */
+ if (wrapped) {
+ *old = *head;
+ *head += mm->len;
+ } else {
+ if (mm->mask)
+ *old &= mm->mask;
+ else
+ *old %= mm->len;
+ if (*old > *head)
+ *head += mm->len;
+ }
+
+ pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+ __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+ return 0;
+
+out_err:
+ pr_err("%s: failed, error %d\n", __func__, err);
+ return err;
+}
+
+static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
+{
+ return rdtsc();
+}
+
+static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
+{
+ struct intel_pt_recording *ptr =
+ container_of(itr, struct intel_pt_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(ptr->evlist, evsel) {
+ if (evsel->attr.type == ptr->intel_pt_pmu->type)
+ return perf_evlist__enable_event_idx(ptr->evlist, evsel,
+ idx);
+ }
+ return -EINVAL;
+}
+
+struct auxtrace_record *intel_pt_recording_init(int *err)
+{
+ struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+ struct intel_pt_recording *ptr;
+
+ if (!intel_pt_pmu)
+ return NULL;
+
+ ptr = zalloc(sizeof(struct intel_pt_recording));
+ if (!ptr) {
+ *err = -ENOMEM;
+ return NULL;
+ }
+
+ ptr->intel_pt_pmu = intel_pt_pmu;
+ ptr->itr.recording_options = intel_pt_recording_options;
+ ptr->itr.info_priv_size = intel_pt_info_priv_size;
+ ptr->itr.info_fill = intel_pt_info_fill;
+ ptr->itr.free = intel_pt_recording_free;
+ ptr->itr.snapshot_start = intel_pt_snapshot_start;
+ ptr->itr.snapshot_finish = intel_pt_snapshot_finish;
+ ptr->itr.find_snapshot = intel_pt_find_snapshot;
+ ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
+ ptr->itr.reference = intel_pt_reference;
+ ptr->itr.read_finish = intel_pt_read_finish;
+ return &ptr->itr;
+}
diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h
new file mode 100644
index 0000000..50cafc2
--- /dev/null
+++ b/tools/perf/util/intel-pt.h
@@ -0,0 +1,35 @@
+/*
+ * intel_pt.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__PERF_INTEL_PT_H__
+#define INCLUDE__PERF_INTEL_PT_H__
+
+#define INTEL_PT_PMU_NAME "intel_pt"
+
+struct auxtrace_record;
+struct perf_tool;
+union perf_event;
+struct perf_session;
+struct perf_event_attr;
+struct perf_pmu;
+
+struct auxtrace_record *intel_pt_recording_init(int *err);
+
+int intel_pt_process_auxtrace_info(union perf_event *event,
+ struct perf_session *session);
+
+struct perf_event_attr *intel_pt_pmu_default_config(struct perf_pmu *pmu);
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 37/44] perf tools: Take Intel PT into use
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (35 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 36/44] perf tools: Add Intel PT support Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 38/44] perf tools: Allow auxtrace data alignment Adrian Hunter
` (6 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
To record an AUX area, the weak function
auxtrace_record__init() must be implemented.
Equally to decode an AUX area, the
AUX area tracing type must be added to the
perf_event__process_auxtrace_info() function.
This patch makes those two changes plus hooks
up default config for the intel_pt PMU. Also
some brief documentation is provided for
using the tools with intel_pt.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/intel-pt.txt | 537 ++++++++++++++++++++++++++++++++++
tools/perf/arch/x86/util/Build | 3 +
tools/perf/arch/x86/util/auxtrace.c | 38 +++
tools/perf/arch/x86/util/pmu.c | 15 +
tools/perf/util/auxtrace.c | 5 +-
5 files changed, 597 insertions(+), 1 deletion(-)
create mode 100644 tools/perf/Documentation/intel-pt.txt
create mode 100644 tools/perf/arch/x86/util/auxtrace.c
create mode 100644 tools/perf/arch/x86/util/pmu.c
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
new file mode 100644
index 0000000..2cd5e34
--- /dev/null
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -0,0 +1,537 @@
+Intel Processor Trace
+=====================
+
+perf record
+===========
+
+new event
+---------
+
+The Intel PT kernel driver creates a new PMU for Intel PT. PMU events are
+selected by providing the PMU name followed by the "config" separated by slashes.
+An enhancement has been made to allow default "config" e.g. the option
+
+ -e intel_pt//
+
+will use a default config value. Currently that is the same as
+
+ -e intel_pt/tsc,noretcomp=0/
+
+which is the same as
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+The config terms are listed in /sys/devices/intel_pt/format. They are bit
+fields within the config member of the struct perf_event_attr which is
+passed to the kernel by the perf_event_open system call. They correspond to bit
+fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions:
+
+ $ for f in `ls /sys/devices/intel_pt/format`;do
+ > echo $f
+ > cat /sys/devices/intel_pt/format/$f
+ > done
+ noretcomp
+ config:11
+ tsc
+ config:10
+
+Note that the default config must be overridden for each term i.e.
+
+ -e intel_pt/noretcomp=0/
+
+is the same as:
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+So, to disable TSC packets use:
+
+ -e intel_pt/tsc=0/
+
+It is also possible to specify the config value explicitly:
+
+ -e intel_pt/config=0x400/
+
+Note that, as with all events, the event is suffixed with event modifiers:
+
+ u userspace
+ k kernel
+ h hypervisor
+ G guest
+ H host
+ p precise ip
+
+'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
+'p' is also not relevant to Intel PT. So only options 'u' and 'k' are
+meaningful for Intel PT.
+
+perf_event_attr is displayed if the -vv option is used e.g.
+
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 120
+ config 0x400
+ sample_period 1
+ sample_freq 1
+ sample_type 0x10087
+ read_format 0x4
+ disabled 1 inherit 1
+ pinned 0 exclusive 0
+ exclude_user 0 exclude_kernel 1
+ exclude_hv 1 exclude_idle 0
+ mmap 0 comm 0
+ mmap2 0 comm_exec 0
+ freq 0 inherit_stat 0
+ enable_on_exec 1 task 0
+ watermark 0 precise_ip 0
+ mmap_data 0 sample_id_all 1
+ exclude_host 0 exclude_guest 0
+ excl.callchain_kern 0 excl.callchain_user 0
+ wakeup_events 0
+ wakeup_watermark 0
+ bp_type 0
+ bp_addr 0
+ config1 0
+ bp_len 0
+ config2 0
+ branch_sample_type 0
+ sample_regs_user 0
+ sample_stack_user 0
+ aux_watermark 0
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 7198 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7198 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7198 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7198 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+
+
+new snapshot option
+-------------------
+
+To select snapshot mode a new option has been added:
+
+ -S
+
+Optionally it can be followed by the snapshot size e.g.
+
+ -S0x100000
+
+The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size
+nor snapshot size is specified, then the default is 4MiB for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced as described in the 'new auxtrace mmap size option' section below.
+
+The snapshot size is displayed if the option -vv is used e.g.
+
+ Intel PT snapshot size: %zu
+
+
+new auxtrace mmap size option
+---------------------------
+
+Intel PT buffer size is specified by an addition to the -m option e.g.
+
+ -m,16
+
+selects a buffer size of 16 pages i.e. 64KiB.
+
+Note that the existing functionality of -m is unchanged. The auxtrace mmap size
+is specified by the optional addition of a comma and the value.
+
+The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+user is likely to get an error as they exceed their mlock limit (Max locked
+memory as shown in /proc/self/limits). Note that perf does not count the first
+512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
+against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
+their mlock limit (which defaults to 64KiB but is not multiplied by the number
+of cpus).
+
+In full-trace mode, powers of two are allowed for buffer size, with a minimum
+size of 2 pages. In snapshot mode, it is the same but the minimum size is
+1 page.
+
+The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
+
+ mmap length 528384
+ auxtrace mmap length 4198400
+
+
+Intel PT modes of operation
+---------------------------
+
+Intel PT can be used in 2 modes:
+ full-trace mode
+ snapshot mode
+
+Full-trace mode traces continuously e.g.
+
+ perf record -e intel_pt//u uname
+
+Snapshot mode captures the available data when a signal is sent e.g.
+
+ perf record -v -e intel_pt//u -S ./loopy 1000000000 &
+ [1] 11435
+ kill -USR2 11435
+ Recording AUX area tracing snapshot
+
+Note that the signal sent is SIGUSR2.
+Note that "Recording AUX area tracing snapshot" is displayed because the -v
+option is used.
+
+None of the 3 modes can be used together.
+
+
+Buffer handling
+---------------
+
+There may be buffer limitations (i.e. single ToPa entry) which means that actual
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER). In order to
+provide other sizes, and in particular an arbitrarily large size, multiple
+buffers are logically concatenated. However an interrupt must be used to switch
+between buffers. That has two potential problems:
+ a) the interrupt may not be handled in time so that the current buffer
+ becomes full and some trace data is lost.
+ b) the interrupts may slow the system and affect the performance
+ results.
+
+If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
+which the tools report as an error.
+
+In full-trace mode, the driver waits for data to be copied out before allowing
+the (logical) buffer to wrap-around. If data is not copied out quickly enough,
+again 'truncated' is set in the PERF_RECORD_AUX event. If the driver has to
+wait, the intel_pt event gets disabled. Because it is difficult to know when
+that happens, perf tools always re-enable the intel_pt event after copying out
+data.
+
+
+Intel PT and build ids
+----------------------
+
+By default "perf record" post-processes the event stream to find all build ids
+for executables for all addresses sampled. Deliberately, Intel PT is not
+decoded for that purpose (it would take too long). Instead the build ids for
+all executables encountered (due to mmap, comm or task events) are included
+in the perf.data file.
+
+To see buildids included in the perf.data file use the command:
+
+ perf buildid-list
+
+If the perf.data file contains Intel PT data, that is the same as:
+
+ perf buildid-list --with-hits
+
+
+Snapshot mode and event disabling
+---------------------------------
+
+In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
+namely PERF_EVENT_IOC_DISABLE. However doing that can also disable the
+collection of side-band information. In order to prevent that, a dummy
+software event has been introduced that permits tracking events (like mmaps) to
+continue to be recorded while intel_pt is disabled. That is important to ensure
+there is complete side-band information to allow the decoding of subsequent
+snapshots.
+
+A test has been created for that. To find the test:
+
+ perf test list
+ ...
+ 23: Test using a dummy software event to keep tracking
+
+To run the test:
+
+ perf test 23
+ 23: Test using a dummy software event to keep tracking : Ok
+
+
+perf record modes (nothing new here)
+------------------------------------
+
+perf record essentially operates in one of three modes:
+ per thread
+ per cpu
+ workload only
+
+"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
+workload).
+"per cpu" is selected by -C or -a.
+"workload only" mode is selected by not using the other options but providing a
+command to run (i.e. the workload).
+
+In per-thread mode an exact list of threads is traced. There is no inheritance.
+Each thread has its own event buffer.
+
+In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
+option, or processes selected with -p or -u) are traced. Each cpu has its own
+buffer. Inheritance is allowed.
+
+In workload-only mode, the workload is traced but with per-cpu buffers.
+Inheritance is allowed. Note that you can now trace a workload in per-thread
+mode by using the --per-thread option.
+
+
+Privileged vs non-privileged users
+----------------------------------
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
+have memory limits imposed upon them. That affects what buffer sizes they can
+have as outlined above.
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
+not permitted to use tracepoints which means there is insufficient side-band
+information to decode Intel PT in per-cpu mode, and potentially workload-only
+mode too if the workload creates new processes.
+
+Note also, that to use tracepoints, read-access to debugfs is required. So if
+debugfs is not mounted or the user does not have read-access, it will again not
+be possible to decode Intel PT in per-cpu mode.
+
+
+sched_switch tracepoint
+-----------------------
+
+The sched_switch tracepoint is used to provide side-band data for Intel PT
+decoding. sched_switch events are automatically added. e.g. the second event
+shown below
+
+ $ perf record -vv -e intel_pt//u uname
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 120
+ config 0x400
+ sample_period 1
+ sample_freq 1
+ sample_type 0x10087
+ read_format 0x4
+ disabled 1 inherit 1
+ pinned 0 exclusive 0
+ exclude_user 0 exclude_kernel 1
+ exclude_hv 1 exclude_idle 0
+ mmap 0 comm 0
+ mmap2 0 comm_exec 0
+ freq 0 inherit_stat 0
+ enable_on_exec 1 task 0
+ watermark 0 precise_ip 0
+ mmap_data 0 sample_id_all 1
+ exclude_host 0 exclude_guest 0
+ excl.callchain_kern 0 excl.callchain_user 0
+ wakeup_events 0
+ wakeup_watermark 0
+ bp_type 0
+ bp_addr 0
+ config1 0
+ bp_len 0
+ config2 0
+ branch_sample_type 0
+ sample_regs_user 0
+ sample_stack_user 0
+ aux_watermark 0
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 7270 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 2
+ size 120
+ config 0x139
+ sample_period 1
+ sample_freq 1
+ sample_type 0x10587
+ read_format 0x4
+ disabled 0 inherit 1
+ pinned 0 exclusive 0
+ exclude_user 0 exclude_kernel 0
+ exclude_hv 0 exclude_idle 0
+ mmap 0 comm 0
+ mmap2 0 comm_exec 0
+ freq 0 inherit_stat 0
+ enable_on_exec 0 task 0
+ watermark 0 precise_ip 0
+ mmap_data 0 sample_id_all 1
+ exclude_host 0 exclude_guest 1
+ excl.callchain_kern 0 excl.callchain_user 0
+ wakeup_events 0
+ wakeup_watermark 0
+ bp_type 0
+ bp_addr 0
+ config1 0
+ bp_len 0
+ config2 0
+ branch_sample_type 0
+ sample_regs_user 0
+ sample_stack_user 0
+ aux_watermark 0
+ ------------------------------------------------------------
+ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 1
+ size 120
+ config 0x9
+ sample_period 1
+ sample_freq 1
+ sample_type 0x10007
+ read_format 0x4
+ disabled 1 inherit 1
+ pinned 0 exclusive 0
+ exclude_user 0 exclude_kernel 1
+ exclude_hv 1 exclude_idle 0
+ mmap 1 comm 1
+ mmap2 1 comm_exec 1
+ freq 0 inherit_stat 0
+ enable_on_exec 1 task 0
+ watermark 0 precise_ip 0
+ mmap_data 0 sample_id_all 1
+ exclude_host 0 exclude_guest 0
+ excl.callchain_kern 0 excl.callchain_user 0
+ wakeup_events 0
+ wakeup_watermark 0
+ bp_type 0
+ bp_addr 0
+ config1 0
+ bp_len 0
+ config2 0
+ branch_sample_type 0
+ sample_regs_user 0
+ sample_stack_user 0
+ aux_watermark 0
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 7270 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 7270 cpu 3 group_fd -1 flags 0x8
+ mmap size 528384B
+ auxtrace mmap length 4194304
+ perf event ring buffer mmapped per cpu
+ Synthesizing auxtrace information
+ Linux
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.045 MB perf.data ]
+
+Note, the sched_switch event is only added if the user is permitted to use it
+and only in per-cpu mode.
+
+Note also, the sched_switch event is only added if TSC packets are requested.
+That is because, in the absence of timing information, the sched_switch events
+cannot be matched against the Intel PT trace.
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by new option -Z.
+
+
+New AUX area option
+----------------------------
+
+Having no option is the same as
+
+ -Z
+
+which, in turn, is the same as
+
+ -Zibxe
+
+The letters are:
+
+ i synthesize "instructions" events
+ b synthesize "branches" events
+ x synthesize "transactions" events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize tracing error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+"Instructions" events look like they were recorded by "perf record -e
+instructions".
+
+"Branches" events look like they were recorded by "perf record -e branches". "c"
+and "r" can be combined to get calls and returns.
+
+"Transactions" events correspond to the start or end of transactions. The
+'flags' field can be used in perf script to determine whether the event is a
+tranasaction start, commit or abort.
+
+Error events are new. They show where the decoder lost the trace. Error events
+are quite important. Users must know if what they are seeing is a complete
+picture or not.
+
+The "d" option will cause the creation of a file "intel_pt.log" containing all
+decoded packets and instructions. Note that this option slows down the decoder
+and that the resulting file may be very large.
+
+In addition, the period of the "instructions" event can be specified. e.g.
+
+ -Zi10us
+
+sets the period to 10us i.e. one instruction sample is synthesized for each 10
+microseconds of trace. Alternatives to "us" are "ms" (milliseconds),
+"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
+
+"ms", "us" and "ns" are converted to TSC ticks.
+
+The timing information included with Intel PT does not give the time of every
+instruction. Consequently, for the purpose of sampling, the decoder estimates
+the time since the last timing packet based on 1 tick per instruction. The time
+on the sample is *not* adjusted and reflects the last known value of TSC.
+
+For Intel PT, the default period is 100us.
+
+Also the call chain size (default 16, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+ -Zig32
+ -Zxg32
+
+To disable trace decoding entirely, use the option --no-auxtrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel PT packets are displayed. The packet decoder does not
+pay attention to PSB packets, but just decodes the bytes - so the packets seen
+by the actual decoder may not be identical in places where the data is corrupt.
+One example of that would be when the buffer-switching interrupt has been too
+slow, and the buffer has been filled completely. In that case, the last packet
+in the buffer might be truncated and immediately followed by a PSB as the trace
+continues in the next buffer.
+
+To disable the display of Intel PT packets, combine the -D option with
+--no-auxtrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option -Z exactly the same as perf script,
+with the exception that the default is -Zge.
+
+
+perf inject
+===========
+
+perf inject also accepts the -Z option in which case tracing data is removed and
+replaced with the synthesized events. e.g.
+
+ perf inject -Z -i perf.data -o perf.data.new
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index cfbccc4..3a59d68 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -1,8 +1,11 @@
libperf-y += header.o
libperf-y += tsc.o
+libperf-y += pmu.o
libperf-y += kvm-stat.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
new file mode 100644
index 0000000..1236b76
--- /dev/null
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -0,0 +1,38 @@
+/*
+ * auxtrace.c: AUX area tracing support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "../../util/header.h"
+#include "../../util/auxtrace.h"
+#include "../../util/intel-pt.h"
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err)
+{
+ char buffer[64];
+ int ret;
+
+ *err = 0;
+
+ ret = get_cpuid(buffer, sizeof(buffer));
+ if (ret) {
+ *err = ret;
+ return NULL;
+ }
+
+ if (!strncmp(buffer, "GenuineIntel,", 13))
+ return intel_pt_recording_init(err);
+
+ return NULL;
+}
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
new file mode 100644
index 0000000..fd11cc3
--- /dev/null
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -0,0 +1,15 @@
+#include <string.h>
+
+#include <linux/perf_event.h>
+
+#include "../../util/intel-pt.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+ if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
+ return intel_pt_pmu_default_config(pmu);
+#endif
+ return NULL;
+}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index e562ec3..9bfe2ac 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -47,6 +47,8 @@
#include "debug.h"
#include "parse-options.h"
+#include "intel-pt.h"
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
@@ -877,7 +879,7 @@ static bool auxtrace__dont_decode(struct perf_session *session)
int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
union perf_event *event,
- struct perf_session *session __maybe_unused)
+ struct perf_session *session)
{
enum auxtrace_type type = event->auxtrace_info.type;
@@ -886,6 +888,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
switch (type) {
case PERF_AUXTRACE_INTEL_PT:
+ return intel_pt_process_auxtrace_info(event, session);
case PERF_AUXTRACE_UNKNOWN:
default:
return -EINVAL;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 38/44] perf tools: Allow auxtrace data alignment
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (36 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 37/44] perf tools: Take Intel PT into use Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 39/44] perf tools: Add Intel BTS support Adrian Hunter
` (5 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Allow auxtrace data to be a multiple of
something other than page size. That is
needed for BTS where the buffer contains
24-byte records.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/auxtrace.c | 7 +++++++
tools/perf/util/auxtrace.h | 1 +
2 files changed, 8 insertions(+)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9bfe2ac..fc52296 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1182,6 +1182,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
data2 = NULL;
}
+ if (itr->alignment) {
+ unsigned int unwanted = len1 % itr->alignment;
+
+ len1 -= unwanted;
+ size -= unwanted;
+ }
+
/* padding must be written by fn() e.g. record__process_auxtrace() */
padding = size & 7;
if (padding)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index ae1249a..fb639c43 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -304,6 +304,7 @@ struct auxtrace_record {
const char *str);
u64 (*reference)(struct auxtrace_record *itr);
int (*read_finish)(struct auxtrace_record *itr, int idx);
+ unsigned int alignment;
};
#ifdef HAVE_AUXTRACE_SUPPORT
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 39/44] perf tools: Add Intel BTS support
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (37 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 38/44] perf tools: Allow auxtrace data alignment Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 40/44] perf tools: Output sample flags and insn_len from intel_pt Adrian Hunter
` (4 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Documentation/intel-bts.txt | 67 ++
tools/perf/arch/x86/util/auxtrace.c | 50 +-
tools/perf/util/Build | 1 +
tools/perf/util/auxtrace.c | 3 +
tools/perf/util/auxtrace.h | 1 +
tools/perf/util/intel-bts.c | 1223 ++++++++++++++++++++++++++++++++
tools/perf/util/intel-bts.h | 31 +
7 files changed, 1373 insertions(+), 3 deletions(-)
create mode 100644 tools/perf/Documentation/intel-bts.txt
create mode 100644 tools/perf/util/intel-bts.c
create mode 100644 tools/perf/util/intel-bts.h
diff --git a/tools/perf/Documentation/intel-bts.txt b/tools/perf/Documentation/intel-bts.txt
new file mode 100644
index 0000000..f349458
--- /dev/null
+++ b/tools/perf/Documentation/intel-bts.txt
@@ -0,0 +1,67 @@
+Intel Branch Trace Store
+========================
+
+perf record
+===========
+
+new event
+---------
+
+The Intel BTS kernel driver creates a new PMU for Intel BTS. The perf record
+option is:
+
+ -e intel_bts//
+
+Currently Intel BTS is limited to per-thread tracing so the --per-thread option
+is also needed.
+
+
+snapshot option
+---------------
+
+The snapshot option is the same as Intel PT (refer Intel PT documentation).
+
+
+auxtrace mmap size option
+-----------------------
+
+The mmap size option is the same as Intel PT (refer Intel PT documentation).
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by option -Z. The -Z option is the same as
+Intel PT (refer Intel PT documentation) except that neither "instructions"
+events nor "transactions" events (and consequently call chains) are supported.
+
+To disable trace decoding entirely, use the option --no-auxtrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel BTS packets are displayed.
+
+To disable the display of Intel BTS packets, combine the -D option with
+--no-auxtrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option -Z exactly the same as perf script.
+
+
+perf inject
+===========
+
+perf inject also accepts the -Z option in which case tracing data is removed and
+replaced with the synthesized events. e.g.
+
+ perf inject -Z -i perf.data -o perf.data.new
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 1236b76..aeb0812 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -13,12 +13,56 @@
*
*/
+#include <stdbool.h>
+
#include "../../util/header.h"
+#include "../../util/debug.h"
+#include "../../util/pmu.h"
#include "../../util/auxtrace.h"
#include "../../util/intel-pt.h"
+#include "../../util/intel-bts.h"
+#include "../../util/evlist.h"
+
+static
+struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
+ int *err)
+{
+ struct perf_pmu *intel_pt_pmu;
+ struct perf_pmu *intel_bts_pmu;
+ struct perf_evsel *evsel;
+ bool found_pt = false;
+ bool found_bts = false;
+
+ intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+ intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+
+ if (evlist) {
+ evlist__for_each(evlist, evsel) {
+ if (intel_pt_pmu &&
+ evsel->attr.type == intel_pt_pmu->type)
+ found_pt = true;
+ if (intel_bts_pmu &&
+ evsel->attr.type == intel_bts_pmu->type)
+ found_bts = true;
+ }
+ }
+
+ if (found_pt && found_bts) {
+ pr_err("intel_pt and intel_bts may not be used together\n");
+ *err = -EINVAL;
+ return NULL;
+ }
+
+ if (found_pt)
+ return intel_pt_recording_init(err);
+
+ if (found_bts)
+ return intel_bts_recording_init(err);
-struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
- int *err)
+ return NULL;
+}
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, int *err)
{
char buffer[64];
int ret;
@@ -32,7 +76,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe
}
if (!strncmp(buffer, "GenuineIntel,", 13))
- return intel_pt_recording_init(err);
+ return auxtrace_record__init_intel(evlist, err);
return NULL;
}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 944bff8..7ee9b78 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -77,6 +77,7 @@ libperf-y += thread-stack.o
libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
libperf-$(CONFIG_AUXTRACE) += intel-pt.o
+libperf-$(CONFIG_AUXTRACE) += intel-bts.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index fc52296..c05df9c 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -48,6 +48,7 @@
#include "parse-options.h"
#include "intel-pt.h"
+#include "intel-bts.h"
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
@@ -889,6 +890,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
switch (type) {
case PERF_AUXTRACE_INTEL_PT:
return intel_pt_process_auxtrace_info(event, session);
+ case PERF_AUXTRACE_INTEL_BTS:
+ return intel_bts_process_auxtrace_info(event, session);
case PERF_AUXTRACE_UNKNOWN:
default:
return -EINVAL;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index fb639c43..318414f 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -40,6 +40,7 @@ struct events_stats;
enum auxtrace_type {
PERF_AUXTRACE_UNKNOWN,
PERF_AUXTRACE_INTEL_PT,
+ PERF_AUXTRACE_INTEL_BTS,
};
enum itrace_period_type {
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
new file mode 100644
index 0000000..dbd8162
--- /dev/null
+++ b/tools/perf/util/intel-bts.c
@@ -0,0 +1,1223 @@
+/*
+ * intel-bts.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <endian.h>
+#include <byteswap.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "cpumap.h"
+#include "color.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "session.h"
+#include "util.h"
+#include "pmu.h"
+#include "debug.h"
+#include "tsc.h"
+#include "auxtrace.h"
+#include "intel-bts.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+#define INTEL_BTS_DFLT_SAMPLE_SIZE KiB(4)
+
+#define INTEL_BTS_MAX_SAMPLE_SIZE KiB(60)
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define le64_to_cpu bswap_64
+#else
+#define le64_to_cpu
+#endif
+
+struct intel_bts_snapshot_ref {
+ void *ref_buf;
+ size_t ref_offset;
+ bool wrapped;
+};
+
+struct intel_bts_recording {
+ struct auxtrace_record itr;
+ struct perf_pmu *intel_bts_pmu;
+ struct perf_evlist *evlist;
+ bool snapshot_mode;
+ size_t snapshot_size;
+ int snapshot_ref_cnt;
+ struct intel_bts_snapshot_ref *snapshot_refs;
+};
+
+struct intel_bts {
+ struct auxtrace auxtrace;
+ struct auxtrace_queues queues;
+ struct auxtrace_heap heap;
+ u32 auxtrace_type;
+ struct perf_session *session;
+ struct machine *machine;
+ bool sampling_mode;
+ bool snapshot_mode;
+ bool data_queued;
+ u32 pmu_type;
+ struct perf_tsc_conversion tc;
+ bool cap_user_time_zero;
+ struct itrace_synth_opts synth_opts;
+ bool sample_branches;
+ u64 branches_sample_type;
+ u64 branches_id;
+ size_t branches_event_size;
+ bool synth_needs_swap;
+};
+
+struct intel_bts_queue {
+ struct intel_bts *bts;
+ unsigned int queue_nr;
+ struct auxtrace_buffer *buffer;
+ bool on_heap;
+ bool done;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ u64 time;
+};
+
+struct branch {
+ u64 from;
+ u64 to;
+ u64 misc;
+};
+
+static void intel_bts_dump(struct intel_bts *bts __maybe_unused,
+ unsigned char *buf, size_t len)
+{
+ struct branch *branch;
+ size_t i, pos = 0, br_sz = sizeof(struct branch), sz;
+ const char *color = PERF_COLOR_BLUE;
+
+ color_fprintf(stdout, color,
+ ". ... Intel BTS data: size %zu bytes\n",
+ len);
+
+ while (len) {
+ if (len >= br_sz)
+ sz = br_sz;
+ else
+ sz = len;
+ printf(".");
+ color_fprintf(stdout, color, " %08x: ", pos);
+ for (i = 0; i < sz; i++)
+ color_fprintf(stdout, color, " %02x", buf[i]);
+ for (; i < br_sz; i++)
+ color_fprintf(stdout, color, " ");
+ if (len >= br_sz) {
+ branch = (struct branch *)buf;
+ color_fprintf(stdout, color, " %"PRIx64" -> %"PRIx64" %s\n",
+ le64_to_cpu(branch->from),
+ le64_to_cpu(branch->to),
+ le64_to_cpu(branch->misc) & 0x10 ?
+ "pred" : "miss");
+ } else {
+ color_fprintf(stdout, color, " Bad record!\n");
+ }
+ pos += sz;
+ buf += sz;
+ len -= sz;
+ }
+}
+
+static void intel_bts_dump_event(struct intel_bts *bts, unsigned char *buf,
+ size_t len)
+{
+ printf(".\n");
+ intel_bts_dump(bts, buf, len);
+}
+
+static int intel_bts_lost(struct intel_bts *bts, struct perf_sample *sample)
+{
+ union perf_event event;
+ int err;
+
+ auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE ,
+ ENOSPC, sample->cpu, sample->pid, sample->tid, 0,
+ "Lost trace data");
+
+ err = perf_session__deliver_synth_event(bts->session, &event, NULL);
+ if (err)
+ pr_err("Intel BTS: failed to deliver error event, error %d\n",
+ err);
+
+ return err;
+}
+
+static struct intel_bts_queue *intel_bts_alloc_queue(struct intel_bts *bts,
+ unsigned int queue_nr)
+{
+ struct intel_bts_queue *btsq;
+
+ btsq = zalloc(sizeof(struct intel_bts_queue));
+ if (!btsq)
+ return NULL;
+
+ btsq->bts = bts;
+ btsq->queue_nr = queue_nr;
+ btsq->pid = -1;
+ btsq->tid = -1;
+ btsq->cpu = -1;
+
+ return btsq;
+}
+
+static int intel_bts_setup_queue(struct intel_bts *bts,
+ struct auxtrace_queue *queue,
+ unsigned int queue_nr)
+{
+ struct intel_bts_queue *btsq = queue->priv;
+
+ if (list_empty(&queue->head))
+ return 0;
+
+ if (!btsq) {
+ btsq = intel_bts_alloc_queue(bts, queue_nr);
+ if (!btsq)
+ return -ENOMEM;
+ queue->priv = btsq;
+
+ if (queue->cpu != -1)
+ btsq->cpu = queue->cpu;
+ btsq->tid = queue->tid;
+ }
+
+ if (bts->sampling_mode)
+ return 0;
+
+ if (!btsq->on_heap && !btsq->buffer) {
+ int ret;
+
+ btsq->buffer = auxtrace_buffer__next(queue, NULL);
+ if (!btsq->buffer)
+ return 0;
+
+ ret = auxtrace_heap__add(&bts->heap, queue_nr,
+ btsq->buffer->reference);
+ if (ret)
+ return ret;
+ btsq->on_heap = true;
+ }
+
+ return 0;
+}
+
+static int intel_bts_setup_queues(struct intel_bts *bts)
+{
+ unsigned int i;
+ int ret;
+
+ for (i = 0; i < bts->queues.nr_queues; i++) {
+ ret = intel_bts_setup_queue(bts, &bts->queues.queue_array[i],
+ i);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static inline int intel_bts_update_queues(struct intel_bts *bts)
+{
+ if (bts->queues.new_data) {
+ bts->queues.new_data = false;
+ return intel_bts_setup_queues(bts);
+ }
+ return 0;
+}
+
+static unsigned char *intel_bts_find_overlap(unsigned char *buf_a, size_t len_a,
+ unsigned char *buf_b, size_t len_b)
+{
+ size_t offs, len;
+
+ if (len_a > len_b)
+ offs = len_a - len_b;
+ else
+ offs = 0;
+
+ for (; offs < len_a; offs += sizeof(struct branch)) {
+ len = len_a - offs;
+ if (!memcmp(buf_a + offs, buf_b, len))
+ return buf_b + len;
+ }
+
+ return buf_b;
+}
+
+static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *b)
+{
+ struct auxtrace_buffer *a;
+ void *start;
+
+ if (b->list.prev == &queue->head)
+ return 0;
+ a = list_entry(b->list.prev, struct auxtrace_buffer, list);
+ start = intel_bts_find_overlap(a->data, a->size, b->data, b->size);
+ if (!start)
+ return -EINVAL;
+ b->use_size = b->data + b->size - start;
+ b->use_data = start;
+ return 0;
+}
+
+static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
+ struct branch *branch)
+{
+ int ret;
+ struct intel_bts *bts = btsq->bts;
+ union perf_event event;
+ struct perf_sample sample = {0};
+
+ event.sample.header.type = PERF_RECORD_SAMPLE;
+ event.sample.header.misc = PERF_RECORD_MISC_USER;
+ event.sample.header.size = sizeof(struct perf_event_header);
+
+ sample.ip = le64_to_cpu(branch->from);
+ sample.pid = btsq->pid;
+ sample.tid = btsq->tid;
+ sample.addr = le64_to_cpu(branch->to);
+ sample.id = btsq->bts->branches_id;
+ sample.stream_id = btsq->bts->branches_id;
+ sample.period = 1;
+ sample.cpu = btsq->cpu;
+
+ if (bts->synth_opts.inject) {
+ event.sample.header.size = bts->branches_event_size;
+ ret = perf_event__synthesize_sample(&event,
+ bts->branches_sample_type,
+ 0, &sample,
+ bts->synth_needs_swap);
+ if (ret)
+ return ret;
+ }
+
+ ret = perf_session__deliver_synth_event(bts->session, &event, &sample);
+ if (ret)
+ pr_err("Intel BTS: failed to deliver branch event, error %d\n",
+ ret);
+
+ return ret;
+}
+
+static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
+ struct auxtrace_buffer *buffer)
+{
+ struct branch *branch;
+ size_t sz;
+ int err = 0;
+
+ if (buffer->use_data) {
+ sz = buffer->use_size;
+ branch = buffer->use_data;
+ } else {
+ sz = buffer->size;
+ branch = buffer->data;
+ }
+
+ if (!btsq->bts->sample_branches)
+ return 0;
+
+ while (sz > sizeof(struct branch)) {
+ if (!branch->from && !branch->to)
+ continue;
+ err = intel_bts_synth_branch_sample(btsq, branch);
+ if (err)
+ break;
+ branch += 1;
+ sz -= sizeof(struct branch);
+ }
+ return err;
+}
+
+static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
+{
+ struct auxtrace_buffer *buffer = btsq->buffer;
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (btsq->done)
+ return 1;
+
+ if (btsq->pid == -1) {
+ struct thread *thread;
+
+ thread = machine__find_thread(btsq->bts->machine, -1, btsq->tid);
+ if (thread)
+ btsq->pid = thread->pid_;
+ }
+
+ queue = &btsq->bts->queues.queue_array[btsq->queue_nr];
+
+ if (!buffer)
+ buffer = auxtrace_buffer__next(queue, NULL);
+
+ if (!buffer) {
+ if (!btsq->bts->sampling_mode)
+ btsq->done = 1;
+ return 1;
+ }
+
+ /* Currently there is no support for split buffers */
+ if (buffer->consecutive)
+ return -EINVAL;
+
+ if (!buffer->data) {
+ int fd = perf_data_file__fd(btsq->bts->session->file);
+
+ buffer->data = auxtrace_buffer__get_data(buffer, fd);
+ if (!buffer->data)
+ return -ENOMEM;
+ }
+
+ if (btsq->bts->snapshot_mode && !buffer->consecutive &&
+ intel_bts_do_fix_overlap(queue, buffer))
+ return -ENOMEM;
+
+ err = intel_bts_process_buffer(btsq, buffer);
+
+ auxtrace_buffer__drop_data(buffer);
+
+ btsq->buffer = auxtrace_buffer__next(queue, buffer);
+ if (btsq->buffer) {
+ if (timestamp)
+ *timestamp = btsq->buffer->reference;
+ } else {
+ if (!btsq->bts->sampling_mode)
+ btsq->done = 1;
+ }
+
+ return err;
+}
+
+static int intel_bts_flush_queue(struct intel_bts_queue *btsq)
+{
+ u64 ts = 0;
+ int ret;
+
+ while (1) {
+ ret = intel_bts_process_queue(btsq, &ts);
+ if (ret < 0)
+ return ret;
+ if (ret)
+ break;
+ }
+ return 0;
+}
+
+static int intel_bts_process_tid_exit(struct intel_bts *bts, pid_t tid)
+{
+ struct auxtrace_queues *queues = &bts->queues;
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ struct auxtrace_queue *queue = &bts->queues.queue_array[i];
+ struct intel_bts_queue *btsq = queue->priv;
+
+ if (btsq && btsq->tid == tid)
+ return intel_bts_flush_queue(btsq);
+ }
+ return 0;
+}
+
+static int intel_bts_process_queues(struct intel_bts *bts, u64 timestamp)
+{
+ while (1) {
+ unsigned int queue_nr;
+ struct auxtrace_queue *queue;
+ struct intel_bts_queue *btsq;
+ u64 ts = 0;
+ int ret;
+
+ if (!bts->heap.heap_cnt)
+ return 0;
+
+ if (bts->heap.heap_array[0].ordinal > timestamp)
+ return 0;
+
+ queue_nr = bts->heap.heap_array[0].queue_nr;
+ queue = &bts->queues.queue_array[queue_nr];
+ btsq = queue->priv;
+
+ auxtrace_heap__pop(&bts->heap);
+
+ ret = intel_bts_process_queue(btsq, &ts);
+ if (ret < 0) {
+ auxtrace_heap__add(&bts->heap, queue_nr, ts);
+ return ret;
+ }
+
+ if (!ret) {
+ ret = auxtrace_heap__add(&bts->heap, queue_nr, ts);
+ if (ret < 0)
+ return ret;
+ } else {
+ btsq->on_heap = false;
+ }
+ }
+
+ return 0;
+}
+
+static int intel_bts_process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+ u64 timestamp;
+ int err;
+
+ if (dump_trace)
+ return 0;
+
+ if (!tool->ordered_events) {
+ pr_err("Intel BTS requires ordered events\n");
+ return -EINVAL;
+ }
+
+ if (sample->time)
+ timestamp = perf_time_to_tsc(sample->time, &bts->tc);
+ else
+ timestamp = 0;
+
+ err = intel_bts_update_queues(bts);
+ if (err)
+ return err;
+
+ err = intel_bts_process_queues(bts, timestamp);
+ if (err)
+ return err;
+ if (event->header.type == PERF_RECORD_EXIT) {
+ err = intel_bts_process_tid_exit(bts, event->comm.tid);
+ if (err)
+ return err;
+ }
+
+ if (event->header.type == PERF_RECORD_AUX &&
+ (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
+ bts->synth_opts.errors)
+ err = intel_bts_lost(bts, sample);
+
+ return err;
+}
+
+static int intel_bts_process_auxtrace_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool __maybe_unused)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+
+ if (bts->sampling_mode)
+ return 0;
+
+ if (!bts->data_queued) {
+ struct auxtrace_buffer *buffer;
+ off_t data_offset;
+ int fd = perf_data_file__fd(session->file);
+ int err;
+
+ if (perf_data_file__is_pipe(session->file)) {
+ data_offset = 0;
+ } else {
+ data_offset = lseek(fd, 0, SEEK_CUR);
+ if (data_offset == -1)
+ return -errno;
+ }
+
+ err = auxtrace_queues__add_event(&bts->queues, session, event,
+ data_offset, &buffer);
+ if (err)
+ return err;
+
+ /* Dump here now we have copied a piped trace out of the pipe */
+ if (dump_trace) {
+ if (auxtrace_buffer__get_data(buffer, fd)) {
+ intel_bts_dump_event(bts, buffer->data,
+ buffer->size);
+ auxtrace_buffer__put_data(buffer);
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int intel_bts_flush(struct perf_session *session __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+ int ret;
+
+ if (dump_trace || bts->sampling_mode)
+ return 0;
+
+ if (!tool->ordered_events)
+ return -EINVAL;
+
+ ret = intel_bts_update_queues(bts);
+ if (ret < 0)
+ return ret;
+
+ return intel_bts_process_queues(bts, MAX_TIMESTAMP);
+}
+
+static void intel_bts_free_queue(void *priv)
+{
+ struct intel_bts_queue *btsq = priv;
+
+ if (!btsq)
+ return;
+ free(btsq);
+}
+
+static void intel_bts_free_events(struct perf_session *session)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+ struct auxtrace_queues *queues = &bts->queues;
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ intel_bts_free_queue(queues->queue_array[i].priv);
+ queues->queue_array[i].priv = NULL;
+ }
+ auxtrace_queues__free(queues);
+}
+
+static void intel_bts_free(struct perf_session *session)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+
+ auxtrace_heap__free(&bts->heap);
+ intel_bts_free_events(session);
+ session->auxtrace = NULL;
+ free(bts);
+}
+
+struct intel_bts_synth {
+ struct perf_tool dummy_tool;
+ struct perf_session *session;
+};
+
+static int intel_bts_event_synth(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+ struct intel_bts_synth *intel_bts_synth =
+ container_of(tool, struct intel_bts_synth, dummy_tool);
+
+ return perf_session__deliver_synth_event(intel_bts_synth->session,
+ event, NULL);
+}
+
+static int intel_bts_synth_event(struct perf_session *session,
+ struct perf_event_attr *attr, u64 id)
+{
+ struct intel_bts_synth intel_bts_synth;
+
+ memset(&intel_bts_synth, 0, sizeof(struct intel_bts_synth));
+ intel_bts_synth.session = session;
+
+ return perf_event__synthesize_attr(&intel_bts_synth.dummy_tool, attr, 1,
+ &id, intel_bts_event_synth);
+}
+
+static int intel_bts_synth_events(struct intel_bts *bts,
+ struct perf_session *session)
+{
+ struct perf_evlist *evlist = session->evlist;
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr;
+ bool found = false;
+ u64 id;
+ int err;
+
+ evlist__for_each(evlist, evsel) {
+ if (evsel->attr.type == bts->pmu_type && evsel->ids) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ pr_debug("There are no selected events with Intel BTS data\n");
+ return 0;
+ }
+
+ memset(&attr, 0, sizeof(struct perf_event_attr));
+ attr.size = sizeof(struct perf_event_attr);
+ attr.type = PERF_TYPE_HARDWARE;
+ attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+ attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+ PERF_SAMPLE_PERIOD;
+ attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+ attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
+ attr.exclude_user = evsel->attr.exclude_user;
+ attr.exclude_kernel = evsel->attr.exclude_kernel;
+ attr.exclude_hv = evsel->attr.exclude_hv;
+ attr.exclude_host = evsel->attr.exclude_host;
+ attr.exclude_guest = evsel->attr.exclude_guest;
+ attr.sample_id_all = evsel->attr.sample_id_all;
+ attr.read_format = evsel->attr.read_format;
+
+ id = evsel->id[0] + 1000000000;
+ if (!id)
+ id = 1;
+
+ if (bts->synth_opts.branches) {
+ attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+ attr.sample_period = 1;
+ attr.sample_type |= PERF_SAMPLE_ADDR;
+ pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+ id, (u64)attr.sample_type);
+ err = intel_bts_synth_event(session, &attr, id);
+ if (err) {
+ pr_err("%s: failed to synthesize 'branches' event type\n",
+ __func__);
+ return err;
+ }
+ bts->sample_branches = true;
+ bts->branches_sample_type = attr.sample_type;
+ bts->branches_id = id;
+ /*
+ * We only use sample types from PERF_SAMPLE_MASK so we can use
+ * __perf_evsel__sample_size() here.
+ */
+ bts->branches_event_size = sizeof(struct sample_event) +
+ __perf_evsel__sample_size(attr.sample_type);
+ }
+
+ bts->synth_needs_swap = evsel->needs_swap;
+
+ return 0;
+}
+
+enum {
+ INTEL_BTS_PMU_TYPE,
+ INTEL_BTS_TIME_SHIFT,
+ INTEL_BTS_TIME_MULT,
+ INTEL_BTS_TIME_ZERO,
+ INTEL_BTS_CAP_USER_TIME_ZERO,
+ INTEL_BTS_SNAPSHOT_MODE,
+ INTEL_BTS_AUXTRACE_PRIV_SIZE,
+};
+
+static const char * const intel_bts_info_fmts[] = {
+ [INTEL_BTS_PMU_TYPE] = " PMU Type %"PRId64"\n",
+ [INTEL_BTS_TIME_SHIFT] = " Time Shift %"PRIu64"\n",
+ [INTEL_BTS_TIME_MULT] = " Time Muliplier %"PRIu64"\n",
+ [INTEL_BTS_TIME_ZERO] = " Time Zero %"PRIu64"\n",
+ [INTEL_BTS_CAP_USER_TIME_ZERO] = " Cap Time Zero %"PRId64"\n",
+ [INTEL_BTS_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n",
+};
+
+static void intel_bts_print_info(u64 *arr, int start, int finish)
+{
+ int i;
+
+ if (!dump_trace)
+ return;
+
+ for (i = start; i <= finish; i++)
+ fprintf(stdout, intel_bts_info_fmts[i], arr[i]);
+}
+
+u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE];
+
+int intel_bts_process_auxtrace_info(union perf_event *event,
+ struct perf_session *session)
+{
+ struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+ size_t min_sz = sizeof(u64) * INTEL_BTS_SNAPSHOT_MODE;
+ struct intel_bts *bts;
+ int err;
+
+ if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+ min_sz)
+ return -EINVAL;
+
+ bts = zalloc(sizeof(struct intel_bts));
+ if (!bts)
+ return -ENOMEM;
+
+ err = auxtrace_queues__init(&bts->queues);
+ if (err)
+ goto err_free;
+
+ bts->session = session;
+ bts->machine = &session->machines.host; /* No kvm support */
+ bts->auxtrace_type = auxtrace_info->type;
+ bts->pmu_type = auxtrace_info->priv[INTEL_BTS_PMU_TYPE];
+ bts->tc.time_shift = auxtrace_info->priv[INTEL_BTS_TIME_SHIFT];
+ bts->tc.time_mult = auxtrace_info->priv[INTEL_BTS_TIME_MULT];
+ bts->tc.time_zero = auxtrace_info->priv[INTEL_BTS_TIME_ZERO];
+ bts->cap_user_time_zero =
+ auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO];
+ bts->snapshot_mode = auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE];
+
+ bts->sampling_mode = false;
+
+ bts->auxtrace.process_event = intel_bts_process_event;
+ bts->auxtrace.process_auxtrace_event = intel_bts_process_auxtrace_event;
+ bts->auxtrace.flush_events = intel_bts_flush;
+ bts->auxtrace.free_events = intel_bts_free_events;
+ bts->auxtrace.free = intel_bts_free;
+ session->auxtrace = &bts->auxtrace;
+
+ intel_bts_print_info(&auxtrace_info->priv[0], INTEL_BTS_PMU_TYPE,
+ INTEL_BTS_SNAPSHOT_MODE);
+
+ if (dump_trace)
+ return 0;
+
+ if (session->itrace_synth_opts && session->itrace_synth_opts->set)
+ bts->synth_opts = *session->itrace_synth_opts;
+ else
+ itrace_synth_opts__set_default(&bts->synth_opts);
+
+ err = intel_bts_synth_events(bts, session);
+ if (err)
+ goto err_free_queues;
+
+ err = auxtrace_queues__process_index(&bts->queues, session);
+ if (err)
+ goto err_free_queues;
+
+ if (bts->queues.populated)
+ bts->data_queued = true;
+
+ return 0;
+
+err_free_queues:
+ auxtrace_queues__free(&bts->queues);
+ session->auxtrace = NULL;
+err_free:
+ free(bts);
+ return err;
+}
+
+static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+{
+ return sizeof(intel_bts_auxtrace_info_priv);
+}
+
+static int intel_bts_info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+ struct perf_event_mmap_page *pc;
+ struct perf_tsc_conversion tc = {0};
+ bool cap_user_time_zero = false;
+ int err;
+
+ if (priv_size != sizeof(intel_bts_auxtrace_info_priv))
+ return -EINVAL;
+
+ if (!session->evlist->nr_mmaps)
+ return -EINVAL;
+
+ pc = session->evlist->mmap[0].base;
+ if (pc) {
+ err = perf_read_tsc_conversion(pc, &tc);
+ if (err) {
+ if (err != -EOPNOTSUPP)
+ return err;
+ } else {
+ cap_user_time_zero = tc.time_mult != 0;
+ }
+ if (!cap_user_time_zero)
+ ui__warning("Intel BTS: TSC not available\n");
+ }
+
+ auxtrace_info->type = PERF_AUXTRACE_INTEL_BTS;
+ auxtrace_info->priv[INTEL_BTS_PMU_TYPE] = intel_bts_pmu->type;
+ auxtrace_info->priv[INTEL_BTS_TIME_SHIFT] = tc.time_shift;
+ auxtrace_info->priv[INTEL_BTS_TIME_MULT] = tc.time_mult;
+ auxtrace_info->priv[INTEL_BTS_TIME_ZERO] = tc.time_zero;
+ auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+ auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE] = btsr->snapshot_mode;
+
+ return 0;
+}
+
+static int intel_bts_recording_options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+ struct perf_evsel *evsel, *intel_bts_evsel = NULL;
+ const struct cpu_map *cpus = evlist->cpus;
+ bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+
+ btsr->evlist = evlist;
+ btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+ evlist__for_each(evlist, evsel) {
+ if (evsel->attr.type == intel_bts_pmu->type) {
+ if (intel_bts_evsel) {
+ pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
+ return -EINVAL;
+ }
+ evsel->attr.freq = 0;
+ evsel->attr.sample_period = 1;
+ intel_bts_evsel = evsel;
+ opts->full_auxtrace = true;
+ }
+ }
+
+ if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+ pr_err("Snapshot mode (-S option) requires " INTEL_BTS_PMU_NAME " PMU event (-e " INTEL_BTS_PMU_NAME ")\n");
+ return -EINVAL;
+ }
+
+ if (!opts->full_auxtrace)
+ return 0;
+
+ if (opts->full_auxtrace && !cpu_map__empty(cpus)) {
+ pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
+ return -EINVAL;
+ }
+
+ /* Set default sizes for snapshot mode */
+ if (opts->auxtrace_snapshot_mode) {
+ if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+ if (privileged) {
+ opts->auxtrace_mmap_pages = MiB(4) / page_size;
+ } else {
+ opts->auxtrace_mmap_pages = KiB(128) / page_size;
+ if (opts->mmap_pages == UINT_MAX)
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ } else if (!opts->auxtrace_mmap_pages && !privileged &&
+ opts->mmap_pages == UINT_MAX) {
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ if (!opts->auxtrace_snapshot_size)
+ opts->auxtrace_snapshot_size =
+ opts->auxtrace_mmap_pages * (size_t)page_size;
+ if (!opts->auxtrace_mmap_pages) {
+ size_t sz = opts->auxtrace_snapshot_size;
+
+ sz = round_up(sz, page_size) / page_size;
+ opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+ }
+ if (opts->auxtrace_snapshot_size >
+ opts->auxtrace_mmap_pages * (size_t)page_size) {
+ pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+ opts->auxtrace_snapshot_size,
+ opts->auxtrace_mmap_pages * (size_t)page_size);
+ return -EINVAL;
+ }
+ if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+ pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+ return -EINVAL;
+ }
+ pr_debug2("Intel BTS snapshot size: %zu\n",
+ opts->auxtrace_snapshot_size);
+ }
+
+ /* Set default sizes for full trace mode */
+ if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+ if (privileged) {
+ opts->auxtrace_mmap_pages = MiB(4) / page_size;
+ } else {
+ opts->auxtrace_mmap_pages = KiB(128) / page_size;
+ if (opts->mmap_pages == UINT_MAX)
+ opts->mmap_pages = KiB(256) / page_size;
+ }
+ }
+
+ /* Validate auxtrace_mmap_pages */
+ if (opts->auxtrace_mmap_pages) {
+ size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+ size_t min_sz;
+
+ if (opts->auxtrace_snapshot_mode)
+ min_sz = KiB(4);
+ else
+ min_sz = KiB(8);
+
+ if (sz < min_sz || !is_power_of_2(sz)) {
+ pr_err("Invalid mmap size for Intel BTS: must be at least %zuKiB and a power of 2\n",
+ min_sz / 1024);
+ return -EINVAL;
+ }
+ }
+
+ if (intel_bts_evsel) {
+ /*
+ * To obtain the auxtrace buffer file descriptor, the auxtrace event
+ * must come first.
+ */
+ perf_evlist__to_front(evlist, intel_bts_evsel);
+ /*
+ * In the case of per-cpu mmaps, we need the CPU on the
+ * AUX event.
+ */
+ if (!cpu_map__empty(cpus))
+ perf_evsel__set_sample_bit(intel_bts_evsel, CPU);
+ }
+
+ /* Add dummy event to keep tracking */
+ if (opts->full_auxtrace) {
+ struct perf_evsel *tracking_evsel;
+ int err;
+
+ err = parse_events(evlist, "dummy:u");
+ if (err)
+ return err;
+
+ tracking_evsel = perf_evlist__last(evlist);
+
+ perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+ tracking_evsel->attr.freq = 0;
+ tracking_evsel->attr.sample_period = 1;
+ }
+
+ return 0;
+}
+
+static int intel_bts_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ unsigned long long snapshot_size = 0;
+ char *endptr;
+
+ if (str) {
+ snapshot_size = strtoull(str, &endptr, 0);
+ if (*endptr || snapshot_size > SIZE_MAX)
+ return -1;
+ }
+
+ opts->auxtrace_snapshot_mode = true;
+ opts->auxtrace_snapshot_size = snapshot_size;
+
+ btsr->snapshot_size = snapshot_size;
+
+ return 0;
+}
+
+static u64 intel_bts_reference(struct auxtrace_record *itr __maybe_unused)
+{
+ return rdtsc();
+}
+
+static int intel_bts_alloc_snapshot_refs(struct intel_bts_recording *btsr,
+ int idx)
+{
+ const size_t sz = sizeof(struct intel_bts_snapshot_ref);
+ int cnt = btsr->snapshot_ref_cnt, new_cnt = cnt * 2;
+ struct intel_bts_snapshot_ref *refs;
+
+ if (!new_cnt)
+ new_cnt = 16;
+
+ while (new_cnt <= idx)
+ new_cnt *= 2;
+
+ refs = calloc(new_cnt, sz);
+ if (!refs)
+ return -ENOMEM;
+
+ memcpy(refs, btsr->snapshot_refs, cnt * sz);
+
+ btsr->snapshot_refs = refs;
+ btsr->snapshot_ref_cnt = new_cnt;
+
+ return 0;
+}
+
+static void intel_bts_free_snapshot_refs(struct intel_bts_recording *btsr)
+{
+ int i;
+
+ for (i = 0; i < btsr->snapshot_ref_cnt; i++)
+ free(btsr->snapshot_refs[i].ref_buf);
+ free(btsr->snapshot_refs);
+}
+
+static void intel_bts_recording_free(struct auxtrace_record *itr)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+
+ intel_bts_free_snapshot_refs(btsr);
+ free(btsr);
+}
+
+static int intel_bts_snapshot_start(struct auxtrace_record *itr)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(btsr->evlist, evsel) {
+ if (evsel->attr.type == btsr->intel_bts_pmu->type)
+ return perf_evlist__disable_event(btsr->evlist, evsel);
+ }
+ return -EINVAL;
+}
+
+static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(btsr->evlist, evsel) {
+ if (evsel->attr.type == btsr->intel_bts_pmu->type)
+ return perf_evlist__enable_event(btsr->evlist, evsel);
+ }
+ return -EINVAL;
+}
+
+static bool intel_bts_first_wrap(u64 *data, size_t buf_size)
+{
+ int i, a, b;
+
+ b = buf_size >> 3;
+ a = b - 512;
+ if (a < 0)
+ a = 0;
+
+ for (i = a; i < b; i++) {
+ if (data[i])
+ return true;
+ }
+
+ return false;
+}
+
+static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 *head, u64 *old)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ bool wrapped;
+ int err;
+
+ pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+ __func__, idx, (size_t)*old, (size_t)*head);
+
+ if (idx >= btsr->snapshot_ref_cnt) {
+ err = intel_bts_alloc_snapshot_refs(btsr, idx);
+ if (err)
+ goto out_err;
+ }
+
+ wrapped = btsr->snapshot_refs[idx].wrapped;
+ if (!wrapped && intel_bts_first_wrap((u64 *)data, mm->len)) {
+ btsr->snapshot_refs[idx].wrapped = true;
+ wrapped = true;
+ }
+
+ /*
+ * In full trace mode 'head' continually increases. However in snapshot
+ * mode 'head' is an offset within the buffer. Here 'old' and 'head'
+ * are adjusted to match the full trace case which expects that 'old' is
+ * always less than 'head'.
+ */
+ if (wrapped) {
+ *old = *head;
+ *head += mm->len;
+ } else {
+ if (mm->mask)
+ *old &= mm->mask;
+ else
+ *old %= mm->len;
+ if (*old > *head)
+ *head += mm->len;
+ }
+
+ pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+ __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+ return 0;
+
+out_err:
+ pr_err("%s: failed, error %d\n", __func__, err);
+ return err;
+}
+
+static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
+{
+ struct intel_bts_recording *btsr =
+ container_of(itr, struct intel_bts_recording, itr);
+ struct perf_evsel *evsel;
+
+ evlist__for_each(btsr->evlist, evsel) {
+ if (evsel->attr.type == btsr->intel_bts_pmu->type)
+ return perf_evlist__enable_event_idx(btsr->evlist,
+ evsel, idx);
+ }
+ return -EINVAL;
+}
+
+struct auxtrace_record *intel_bts_recording_init(int *err)
+{
+ struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+ struct intel_bts_recording *btsr;
+
+ if (!intel_bts_pmu)
+ return NULL;
+
+ btsr = zalloc(sizeof(struct intel_bts_recording));
+ if (!btsr) {
+ *err = -ENOMEM;
+ return NULL;
+ }
+
+ btsr->intel_bts_pmu = intel_bts_pmu;
+ btsr->itr.recording_options = intel_bts_recording_options;
+ btsr->itr.info_priv_size = intel_bts_info_priv_size;
+ btsr->itr.info_fill = intel_bts_info_fill;
+ btsr->itr.free = intel_bts_recording_free;
+ btsr->itr.snapshot_start = intel_bts_snapshot_start;
+ btsr->itr.snapshot_finish = intel_bts_snapshot_finish;
+ btsr->itr.find_snapshot = intel_bts_find_snapshot;
+ btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
+ btsr->itr.reference = intel_bts_reference;
+ btsr->itr.read_finish = intel_bts_read_finish;
+ btsr->itr.alignment = sizeof(struct branch);
+ return &btsr->itr;
+}
diff --git a/tools/perf/util/intel-bts.h b/tools/perf/util/intel-bts.h
new file mode 100644
index 0000000..0bbf838
--- /dev/null
+++ b/tools/perf/util/intel-bts.h
@@ -0,0 +1,31 @@
+/*
+ * intel-bts.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__PERF_INTEL_BTS_H__
+#define INCLUDE__PERF_INTEL_BTS_H__
+
+#define INTEL_BTS_PMU_NAME "intel_bts"
+
+struct auxtrace_record;
+struct perf_tool;
+union perf_event;
+struct perf_session;
+
+struct auxtrace_record *intel_bts_recording_init(int *err);
+
+int intel_bts_process_auxtrace_info(union perf_event *event,
+ struct perf_session *session);
+
+#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 40/44] perf tools: Output sample flags and insn_len from intel_pt
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (38 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 39/44] perf tools: Add Intel BTS support Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 41/44] perf tools: Output sample flags and insn_len from intel_bts Adrian Hunter
` (3 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
intel_pt synthesizes samples. Fill in the new flags and
insn_len members with instruction information.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-pt.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 1ad8cbd..11c0445 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -912,6 +912,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
sample.stream_id = ptq->pt->branches_id;
sample.period = 1;
sample.cpu = ptq->cpu;
+ sample.flags = ptq->flags;
+ sample.insn_len = ptq->insn_len;
if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
return 0;
@@ -954,6 +956,8 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
sample.stream_id = ptq->pt->instructions_id;
sample.period = ptq->pt->instructions_sample_period;
sample.cpu = ptq->cpu;
+ sample.flags = ptq->flags;
+ sample.insn_len = ptq->insn_len;
if (pt->synth_opts.callchain) {
thread_stack__sample(ptq->thread, ptq->chain,
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 41/44] perf tools: Output sample flags and insn_len from intel_bts
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (39 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 40/44] perf tools: Output sample flags and insn_len from intel_pt Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 42/44] perf tools: Intel PT to always update thread stack trace number Adrian Hunter
` (2 subsequent siblings)
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
intel_bts synthesizes samples. Fill in the new flags and
insn_len members with instruction information.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-bts.c | 128 ++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 124 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index dbd8162..a2ac54a 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -26,11 +26,13 @@
#include "evlist.h"
#include "machine.h"
#include "session.h"
+#include "color.h"
#include "util.h"
#include "pmu.h"
#include "debug.h"
#include "tsc.h"
#include "auxtrace.h"
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
#include "intel-bts.h"
#define MAX_TIMESTAMP (~0ULL)
@@ -81,6 +83,7 @@ struct intel_bts {
bool cap_user_time_zero;
struct itrace_synth_opts synth_opts;
bool sample_branches;
+ u32 branches_filter;
u64 branches_sample_type;
u64 branches_id;
size_t branches_event_size;
@@ -97,6 +100,8 @@ struct intel_bts_queue {
pid_t tid;
int cpu;
u64 time;
+ struct intel_pt_insn intel_pt_insn;
+ u32 sample_flags;
};
struct branch {
@@ -304,6 +309,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
sample.stream_id = btsq->bts->branches_id;
sample.period = 1;
sample.cpu = btsq->cpu;
+ sample.flags = btsq->sample_flags;
+ sample.insn_len = btsq->intel_pt_insn.length;
if (bts->synth_opts.inject) {
event.sample.header.size = bts->branches_event_size;
@@ -323,11 +330,116 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
return ret;
}
+static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
+{
+ struct machine *machine = btsq->bts->machine;
+ struct thread *thread;
+ struct addr_location al;
+ unsigned char buf[1024];
+ size_t bufsz;
+ ssize_t len;
+ int x86_64;
+ uint8_t cpumode;
+
+ bufsz = intel_pt_insn_max_size();
+
+ if (machine__kernel_ip(machine, ip))
+ cpumode = PERF_RECORD_MISC_KERNEL;
+ else
+ cpumode = PERF_RECORD_MISC_USER;
+
+ thread = machine__find_thread(machine, -1, btsq->tid);
+ if (!thread)
+ return -1;
+
+ thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
+ if (!al.map || !al.map->dso)
+ return -1;
+
+ len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz);
+ if (len <= 0)
+ return -1;
+
+ /* Load maps to ensure dso->is_64_bit has been updated */
+ map__load(al.map, machine->symbol_filter);
+
+ x86_64 = al.map->dso->is_64_bit;
+
+ if (intel_pt_get_insn(buf, len, x86_64, &btsq->intel_pt_insn))
+ return -1;
+
+ return 0;
+}
+
+static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
+ pid_t tid, u64 ip)
+{
+ union perf_event event;
+ const char *msg = "Failed to get instruction";
+ int code = EILSEQ;
+ int err;
+
+ auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE , code,
+ cpu, pid, tid, ip, msg);
+
+ err = perf_session__deliver_synth_event(bts->session, &event, NULL);
+ if (err)
+ pr_err("Intel BTS: failed to deliver error event, error %d\n",
+ err);
+
+ return err;
+}
+
+static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
+ struct branch *branch)
+{
+ int err;
+
+ if (!branch->from) {
+ if (branch->to)
+ btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_TRACE_BEGIN;
+ else
+ btsq->sample_flags = 0;
+ btsq->intel_pt_insn.length = 0;
+ } else if (!branch->to) {
+ btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_TRACE_END;
+ btsq->intel_pt_insn.length = 0;
+ } else {
+ err = intel_bts_get_next_insn(btsq, branch->from);
+ if (err) {
+ btsq->sample_flags = 0;
+ btsq->intel_pt_insn.length = 0;
+ if (!btsq->bts->synth_opts.errors)
+ return 0;
+ err = intel_bts_synth_error(btsq->bts, btsq->cpu,
+ btsq->pid, btsq->tid,
+ branch->from);
+ return err;
+ }
+ btsq->sample_flags = intel_pt_insn_type(btsq->intel_pt_insn.op);
+ /* Check for an async branch into the kernel */
+ if (!machine__kernel_ip(btsq->bts->machine, branch->from) &&
+ machine__kernel_ip(btsq->bts->machine, branch->to) &&
+ btsq->sample_flags != (PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_CALL |
+ PERF_IP_FLAG_SYSCALLRET))
+ btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+ PERF_IP_FLAG_CALL |
+ PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_INTERRUPT;
+ }
+
+ return 0;
+}
+
static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
struct auxtrace_buffer *buffer)
{
struct branch *branch;
- size_t sz;
+ size_t sz, bsz = sizeof(struct branch);
+ u32 filter = btsq->bts->branches_filter;
int err = 0;
if (buffer->use_data) {
@@ -341,14 +453,15 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
if (!btsq->bts->sample_branches)
return 0;
- while (sz > sizeof(struct branch)) {
+ for (; sz > bsz; branch += 1, sz -= bsz) {
if (!branch->from && !branch->to)
continue;
+ intel_bts_get_branch_type(btsq, branch);
+ if (filter && !(filter & btsq->sample_flags))
+ continue;
err = intel_bts_synth_branch_sample(btsq, branch);
if (err)
break;
- branch += 1;
- sz -= sizeof(struct branch);
}
return err;
}
@@ -804,6 +917,13 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
else
itrace_synth_opts__set_default(&bts->synth_opts);
+ if (bts->synth_opts.calls)
+ bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_TRACE_END;
+ if (bts->synth_opts.returns)
+ bts->branches_filter |= PERF_IP_FLAG_RETURN |
+ PERF_IP_FLAG_TRACE_BEGIN;
+
err = intel_bts_synth_events(bts, session);
if (err)
goto err_free_queues;
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 42/44] perf tools: Intel PT to always update thread stack trace number
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (40 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 41/44] perf tools: Output sample flags and insn_len from intel_bts Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 43/44] perf tools: Intel BTS " Adrian Hunter
2015-04-09 15:54 ` [PATCH 44/44] perf tools: Add example call-graph script Adrian Hunter
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
The enhanced thread stack is used by higher layers but still
requires the trace number. The trace number is used to
distinguish discontinuous sections of trace (for example
from Snapshot mode or Sample mode), which cause the thread
stack to be flushed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-pt.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 11c0445..5994356 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -302,7 +302,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
!buffer->consecutive)) {
b->consecutive = false;
- b->trace_nr = buffer->buffer_nr;
+ b->trace_nr = buffer->buffer_nr + 1;
} else {
b->consecutive = true;
}
@@ -1101,6 +1101,8 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
state->to_ip, ptq->insn_len,
state->trace_nr);
+ else
+ thread_stack__set_trace_nr(ptq->thread, state->trace_nr);
if (pt->sample_branches) {
err = intel_pt_synth_branch_sample(ptq);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 43/44] perf tools: Intel BTS to always update thread stack trace number
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (41 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 42/44] perf tools: Intel PT to always update thread stack trace number Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
2015-04-09 15:54 ` [PATCH 44/44] perf tools: Add example call-graph script Adrian Hunter
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
The enhanced thread stack is used by higher layers but still
requires the trace number. The trace number is used to
distinguish discontinuous sections of trace (for example
from Snapshot mode or Sample mode), which cause the thread
stack to be flushed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/intel-bts.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index a2ac54a..8eb7dba 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -28,6 +28,8 @@
#include "session.h"
#include "color.h"
#include "util.h"
+#include "thread.h"
+#include "thread-stack.h"
#include "pmu.h"
#include "debug.h"
#include "tsc.h"
@@ -468,19 +470,22 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
{
- struct auxtrace_buffer *buffer = btsq->buffer;
+ struct auxtrace_buffer *buffer = btsq->buffer, *old_buffer = buffer;
struct auxtrace_queue *queue;
+ struct thread *thread;
int err;
if (btsq->done)
return 1;
if (btsq->pid == -1) {
- struct thread *thread;
-
- thread = machine__find_thread(btsq->bts->machine, -1, btsq->tid);
+ thread = machine__find_thread(btsq->bts->machine, -1,
+ btsq->tid);
if (thread)
btsq->pid = thread->pid_;
+ } else {
+ thread = machine__findnew_thread(btsq->bts->machine, btsq->pid,
+ btsq->tid);
}
queue = &btsq->bts->queues.queue_array[btsq->queue_nr];
@@ -510,6 +515,11 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
intel_bts_do_fix_overlap(queue, buffer))
return -ENOMEM;
+ if (!btsq->bts->synth_opts.callchain && thread &&
+ (!old_buffer || btsq->bts->sampling_mode ||
+ (btsq->bts->snapshot_mode && !buffer->consecutive)))
+ thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
+
err = intel_bts_process_buffer(btsq, buffer);
auxtrace_buffer__drop_data(buffer);
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread* [PATCH 44/44] perf tools: Add example call-graph script
2015-04-09 15:53 [PATCH 00/44] perf tools: Introduce an abstraction for AUX Area and Instruction Tracing Adrian Hunter
` (42 preceding siblings ...)
2015-04-09 15:54 ` [PATCH 43/44] perf tools: Intel BTS " Adrian Hunter
@ 2015-04-09 15:54 ` Adrian Hunter
43 siblings, 0 replies; 79+ messages in thread
From: Adrian Hunter @ 2015-04-09 15:54 UTC (permalink / raw)
To: Peter Zijlstra, Arnaldo Carvalho de Melo
Cc: linux-kernel, David Ahern, Frederic Weisbecker, Jiri Olsa,
Namhyung Kim, Stephane Eranian
Add a python script which will display a context-sensitive
call-graph using data from a postrgreql database created
by the export-to-postgresql.py script.
Example:
# Record 'ls' command
~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
# Create and export to database 'pt_ls'
~/libexec/perf-core/perf-with-kcore script pt_ls -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py pt_ls branches calls
# Display call-graph from database 'pt_ls'
python tools/perf/scripts/python/call-graph-from-postgresql.py pt_ls
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
.../scripts/python/call-graph-from-postgresql.py | 285 +++++++++++++++++++++
1 file changed, 285 insertions(+)
create mode 100644 tools/perf/scripts/python/call-graph-from-postgresql.py
diff --git a/tools/perf/scripts/python/call-graph-from-postgresql.py b/tools/perf/scripts/python/call-graph-from-postgresql.py
new file mode 100644
index 0000000..5e8cfdf
--- /dev/null
+++ b/tools/perf/scripts/python/call-graph-from-postgresql.py
@@ -0,0 +1,285 @@
+#!/usr/bin/python2
+# call-graph-from-postgresql.py: create call-graph from postgresql database
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+# more details.
+
+import sys
+from PySide.QtCore import *
+from PySide.QtGui import *
+from PySide.QtSql import *
+from decimal import *
+
+class TreeItem():
+
+ def __init__(self, db, row, parent_item):
+ self.db = db
+ self.row = row
+ self.parent_item = parent_item
+ self.query_done = False;
+ self.child_count = 0
+ self.child_items = []
+ self.data = ["", "", "", "", "", "", ""]
+ self.comm_id = 0
+ self.thread_id = 0
+ self.call_path_id = 1
+ self.branch_count = 0
+ self.time = 0
+ if not parent_item:
+ self.setUpRoot()
+
+ def setUpRoot(self):
+ self.query_done = True
+ query = QSqlQuery(self.db)
+ ret = query.exec_('SELECT id, comm FROM comms')
+ if not ret:
+ raise Exception("Query failed: " + query.lastError().text())
+ while query.next():
+ if not query.value(0):
+ continue
+ child_item = TreeItem(self.db, self.child_count, self)
+ self.child_items.append(child_item)
+ self.child_count += 1
+ child_item.setUpLevel1(query.value(0), query.value(1))
+
+ def setUpLevel1(self, comm_id, comm):
+ self.query_done = True;
+ self.comm_id = comm_id
+ self.data[0] = comm
+ self.child_items = []
+ self.child_count = 0
+ query = QSqlQuery(self.db)
+ ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
+ if not ret:
+ raise Exception("Query failed: " + query.lastError().text())
+ while query.next():
+ child_item = TreeItem(self.db, self.child_count, self)
+ self.child_items.append(child_item)
+ self.child_count += 1
+ child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
+
+ def setUpLevel2(self, comm_id, thread_id, pid, tid):
+ self.comm_id = comm_id
+ self.thread_id = thread_id
+ self.data[0] = str(pid) + ":" + str(tid)
+
+ def getChildItem(self, row):
+ return self.child_items[row]
+
+ def getParentItem(self):
+ return self.parent_item
+
+ def getRow(self):
+ return self.row
+
+ def timePercent(self, b):
+ if not self.time:
+ return "0.0"
+ x = (b * Decimal(100)) / self.time
+ return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
+
+ def branchPercent(self, b):
+ if not self.branch_count:
+ return "0.0"
+ x = (b * Decimal(100)) / self.branch_count
+ return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
+
+ def addChild(self, call_path_id, name, dso, count, time, branch_count):
+ child_item = TreeItem(self.db, self.child_count, self)
+ child_item.comm_id = self.comm_id
+ child_item.thread_id = self.thread_id
+ child_item.call_path_id = call_path_id
+ child_item.branch_count = branch_count
+ child_item.time = time
+ child_item.data[0] = name
+ if dso == "[kernel.kallsyms]":
+ dso = "[kernel]"
+ child_item.data[1] = dso
+ child_item.data[2] = str(count)
+ child_item.data[3] = str(time)
+ child_item.data[4] = self.timePercent(time)
+ child_item.data[5] = str(branch_count)
+ child_item.data[6] = self.branchPercent(branch_count)
+ self.child_items.append(child_item)
+ self.child_count += 1
+
+ def selectCalls(self):
+ self.query_done = True;
+ query = QSqlQuery(self.db)
+ ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
+ '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
+ '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
+ '( SELECT ip FROM call_paths where id = call_path_id ) '
+ 'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
+ 'ORDER BY call_path_id')
+ if not ret:
+ raise Exception("Query failed: " + query.lastError().text())
+ last_call_path_id = 0
+ name = ""
+ dso = ""
+ count = 0
+ branch_count = 0
+ total_branch_count = 0
+ time = 0
+ total_time = 0
+ while query.next():
+ if query.value(1) == last_call_path_id:
+ count += 1
+ branch_count += query.value(2)
+ time += query.value(4) - query.value(3)
+ else:
+ if count:
+ self.addChild(last_call_path_id, name, dso, count, time, branch_count)
+ last_call_path_id = query.value(1)
+ name = query.value(5)
+ dso = query.value(6)
+ count = 1
+ total_branch_count += branch_count
+ total_time += time
+ branch_count = query.value(2)
+ time = query.value(4) - query.value(3)
+ if count:
+ self.addChild(last_call_path_id, name, dso, count, time, branch_count)
+ total_branch_count += branch_count
+ total_time += time
+ # Top level does not have time or branch count, so fix that here
+ if total_branch_count > self.branch_count:
+ self.branch_count = total_branch_count
+ if self.branch_count:
+ for child_item in self.child_items:
+ child_item.data[6] = self.branchPercent(child_item.branch_count)
+ if total_time > self.time:
+ self.time = total_time
+ if self.time:
+ for child_item in self.child_items:
+ child_item.data[4] = self.timePercent(child_item.time)
+
+ def childCount(self):
+ if not self.query_done:
+ self.selectCalls()
+ return self.child_count
+
+ def columnCount(self):
+ return 7
+
+ def columnHeader(self, column):
+ headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+ return headers[column]
+
+ def getData(self, column):
+ return self.data[column]
+
+class TreeModel(QAbstractItemModel):
+
+ def __init__(self, db, parent=None):
+ super(TreeModel, self).__init__(parent)
+ self.db = db
+ self.root = TreeItem(db, 0, None)
+
+ def columnCount(self, parent):
+ return self.root.columnCount()
+
+ def rowCount(self, parent):
+ if parent.isValid():
+ parent_item = parent.internalPointer()
+ else:
+ parent_item = self.root
+ return parent_item.childCount()
+
+ def headerData(self, section, orientation, role):
+ if role == Qt.TextAlignmentRole:
+ if section > 1:
+ return Qt.AlignRight
+ if role != Qt.DisplayRole:
+ return None
+ if orientation != Qt.Horizontal:
+ return None
+ return self.root.columnHeader(section)
+
+ def parent(self, child):
+ child_item = child.internalPointer()
+ if child_item is self.root:
+ return QModelIndex()
+ parent_item = child_item.getParentItem()
+ return self.createIndex(parent_item.getRow(), 0, parent_item)
+
+ def index(self, row, column, parent):
+ if parent.isValid():
+ parent_item = parent.internalPointer()
+ else:
+ parent_item = self.root
+ child_item = parent_item.getChildItem(row)
+ return self.createIndex(row, column, child_item)
+
+ def data(self, index, role):
+ if role == Qt.TextAlignmentRole:
+ if index.column() > 1:
+ return Qt.AlignRight
+ if role != Qt.DisplayRole:
+ return None
+ index_item = index.internalPointer()
+ return index_item.getData(index.column())
+
+class MainWindow(QMainWindow):
+
+ def __init__(self, db, dbname, parent=None):
+ super(MainWindow, self).__init__(parent)
+
+ self.setObjectName("MainWindow")
+ self.setWindowTitle("Call Graph: " + dbname)
+ self.move(100, 100)
+ self.resize(800, 600)
+ style = self.style()
+ icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
+ self.setWindowIcon(icon);
+
+ self.model = TreeModel(db)
+
+ self.view = QTreeView()
+ self.view.setModel(self.model)
+
+ self.setCentralWidget(self.view)
+
+if __name__ == '__main__':
+ if (len(sys.argv) < 2):
+ print >> sys.stderr, "Usage is: call-graph-from-postgresql.py <database name>"
+ raise Exception("Too few arguments")
+
+ dbname = sys.argv[1]
+
+ db = QSqlDatabase.addDatabase('QPSQL')
+
+ opts = dbname.split()
+ for opt in opts:
+ if '=' in opt:
+ opt = opt.split('=')
+ if opt[0] == 'hostname':
+ db.setHostName(opt[1])
+ elif opt[0] == 'port':
+ db.setPort(int(opt[1]))
+ elif opt[0] == 'username':
+ db.setUserName(opt[1])
+ elif opt[0] == 'password':
+ db.setPassword(opt[1])
+ elif opt[0] == 'dbname':
+ dbname = opt[1]
+ else:
+ dbname = opt
+
+ db.setDatabaseName(dbname)
+ if not db.open():
+ raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+
+ app = QApplication(sys.argv)
+ window = MainWindow(db, dbname)
+ window.show()
+ err = app.exec_()
+ db.close()
+ sys.exit(err)
--
1.9.1
^ permalink raw reply related [flat|nested] 79+ messages in thread