From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/tools/perf/util/intel-pt.c | 1483 +++++++++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 1,225 insertions(+), 258 deletions(-)
diff --git a/kernel/tools/perf/util/intel-pt.c b/kernel/tools/perf/util/intel-pt.c
index 256b475..453773c 100644
--- a/kernel/tools/perf/util/intel-pt.c
+++ b/kernel/tools/perf/util/intel-pt.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* intel_pt.c: Intel Processor 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 <inttypes.h>
@@ -18,9 +9,10 @@
#include <stdbool.h>
#include <errno.h>
#include <linux/kernel.h>
+#include <linux/string.h>
#include <linux/types.h>
+#include <linux/zalloc.h>
-#include "../perf.h"
#include "session.h"
#include "machine.h"
#include "memswap.h"
@@ -31,7 +23,6 @@
#include "evsel.h"
#include "map.h"
#include "color.h"
-#include "util.h"
#include "thread.h"
#include "thread-stack.h"
#include "symbol.h"
@@ -42,6 +33,11 @@
#include "tsc.h"
#include "intel-pt.h"
#include "config.h"
+#include "util/perf_api_probe.h"
+#include "util/synthetic-events.h"
+#include "time-utils.h"
+
+#include "../arch/x86/include/uapi/asm/perf_regs.h"
#include "intel-pt-decoder/intel-pt-log.h"
#include "intel-pt-decoder/intel-pt-decoder.h"
@@ -50,6 +46,11 @@
#define MAX_TIMESTAMP (~0ULL)
+struct range {
+ u64 start;
+ u64 end;
+};
+
struct intel_pt {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
@@ -57,7 +58,7 @@
u32 auxtrace_type;
struct perf_session *session;
struct machine *machine;
- struct perf_evsel *switch_evsel;
+ struct evsel *switch_evsel;
struct thread *unknown_thread;
bool timeless_decoding;
bool sampling_mode;
@@ -68,6 +69,10 @@
bool est_tsc;
bool sync_switch;
bool mispred_all;
+ bool use_thread_stack;
+ bool callstack;
+ unsigned int br_stack_sz;
+ unsigned int br_stack_sz_plus;
int have_sched_switch;
u32 pmu_type;
u64 kernel_start;
@@ -104,6 +109,9 @@
u64 pwrx_id;
u64 cbr_id;
+ bool sample_pebs;
+ struct evsel *pebs_evsel;
+
u64 tsc_bit;
u64 mtc_bit;
u64 mtc_freq_bits;
@@ -118,6 +126,12 @@
char *filter;
struct addr_filters filts;
+
+ struct range *time_ranges;
+ unsigned int range_cnt;
+
+ struct ip_callchain *chain;
+ struct branch_stack *br_stack;
};
enum switch_state {
@@ -137,8 +151,6 @@
const struct intel_pt_state *state;
struct ip_callchain *chain;
struct branch_stack *last_branch;
- struct branch_stack *last_branch_rb;
- size_t last_branch_pos;
union perf_event *event_buf;
bool on_heap;
bool stop;
@@ -154,9 +166,19 @@
bool have_sample;
u64 time;
u64 timestamp;
+ u64 sel_timestamp;
+ bool sel_start;
+ unsigned int sel_idx;
u32 flags;
u16 insn_len;
u64 last_insn_cnt;
+ u64 ipc_insn_cnt;
+ u64 ipc_cyc_cnt;
+ u64 last_in_insn_cnt;
+ u64 last_in_cyc_cnt;
+ u64 last_br_insn_cnt;
+ u64 last_br_cyc_cnt;
+ unsigned int cbr_seen;
char insn[INTEL_PT_INSN_BUF_SZ];
};
@@ -168,13 +190,14 @@
int ret, pkt_len, i;
char desc[INTEL_PT_PKT_DESC_MAX];
const char *color = PERF_COLOR_BLUE;
+ enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
color_fprintf(stdout, color,
". ... Intel Processor Trace data: size %zu bytes\n",
len);
while (len) {
- ret = intel_pt_get_packet(buf, len, &packet);
+ ret = intel_pt_get_packet(buf, len, &packet, &ctx);
if (ret > 0)
pkt_len = ret;
else
@@ -206,6 +229,44 @@
intel_pt_dump(pt, buf, len);
}
+static void intel_pt_log_event(union perf_event *event)
+{
+ FILE *f = intel_pt_log_fp();
+
+ if (!intel_pt_enable_logging || !f)
+ return;
+
+ perf_event__fprintf(event, NULL, f);
+}
+
+static void intel_pt_dump_sample(struct perf_session *session,
+ struct perf_sample *sample)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+
+ printf("\n");
+ intel_pt_dump(pt, sample->aux_sample.data, sample->aux_sample.size);
+}
+
+static bool intel_pt_log_events(struct intel_pt *pt, u64 tm)
+{
+ struct perf_time_interval *range = pt->synth_opts.ptime_range;
+ int n = pt->synth_opts.range_num;
+
+ if (pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
+ return true;
+
+ if (pt->synth_opts.log_minus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
+ return false;
+
+ /* perf_time__ranges_skip_sample does not work if time is zero */
+ if (!tm)
+ tm = 1;
+
+ return !n || !perf_time__ranges_skip_sample(range, n, tm);
+}
+
static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
struct auxtrace_buffer *b)
{
@@ -223,31 +284,12 @@
return 0;
}
-/* This function assumes data is processed sequentially only */
-static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+static int intel_pt_get_buffer(struct intel_pt_queue *ptq,
+ struct auxtrace_buffer *buffer,
+ struct auxtrace_buffer *old_buffer,
+ struct intel_pt_buffer *b)
{
- struct intel_pt_queue *ptq = data;
- struct auxtrace_buffer *buffer = ptq->buffer;
- struct auxtrace_buffer *old_buffer = ptq->old_buffer;
- struct auxtrace_queue *queue;
bool might_overlap;
-
- 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__fd(ptq->pt->session->data);
@@ -277,6 +319,95 @@
} else {
b->consecutive = true;
}
+
+ return 0;
+}
+
+/* Do not drop buffers with references - refer intel_pt_get_trace() */
+static void intel_pt_lookahead_drop_buffer(struct intel_pt_queue *ptq,
+ struct auxtrace_buffer *buffer)
+{
+ if (!buffer || buffer == ptq->buffer || buffer == ptq->old_buffer)
+ return;
+
+ auxtrace_buffer__drop_data(buffer);
+}
+
+/* Must be serialized with respect to intel_pt_get_trace() */
+static int intel_pt_lookahead(void *data, intel_pt_lookahead_cb_t cb,
+ void *cb_data)
+{
+ struct intel_pt_queue *ptq = data;
+ struct auxtrace_buffer *buffer = ptq->buffer;
+ struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+ struct auxtrace_queue *queue;
+ int err = 0;
+
+ queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+ while (1) {
+ struct intel_pt_buffer b = { .len = 0 };
+
+ buffer = auxtrace_buffer__next(queue, buffer);
+ if (!buffer)
+ break;
+
+ err = intel_pt_get_buffer(ptq, buffer, old_buffer, &b);
+ if (err)
+ break;
+
+ if (b.len) {
+ intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+ old_buffer = buffer;
+ } else {
+ intel_pt_lookahead_drop_buffer(ptq, buffer);
+ continue;
+ }
+
+ err = cb(&b, cb_data);
+ if (err)
+ break;
+ }
+
+ if (buffer != old_buffer)
+ intel_pt_lookahead_drop_buffer(ptq, buffer);
+ intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+
+ return err;
+}
+
+/*
+ * This function assumes data is processed sequentially only.
+ * Must be serialized with respect to intel_pt_lookahead()
+ */
+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;
+ struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+ struct auxtrace_queue *queue;
+ int err;
+
+ 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;
+
+ err = intel_pt_get_buffer(ptq, buffer, old_buffer, b);
+ if (err)
+ return err;
if (ptq->step_through_buffers)
ptq->stop = true;
@@ -405,6 +536,17 @@
return NULL;
return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
+}
+
+static void intel_pt_cache_invalidate(struct dso *dso, struct machine *machine,
+ u64 offset)
+{
+ struct auxtrace_cache *c = intel_pt_cache(dso, machine);
+
+ if (!c)
+ return;
+
+ auxtrace_cache__remove(dso->auxtrace_cache, offset);
}
static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
@@ -629,11 +771,11 @@
static bool intel_pt_exclude_kernel(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
- !evsel->attr.exclude_kernel)
+ if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
+ !evsel->core.attr.exclude_kernel)
return false;
}
return true;
@@ -641,14 +783,14 @@
static bool intel_pt_return_compression(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
u64 config;
if (!pt->noretcomp_bit)
return true;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
(config & pt->noretcomp_bit))
return false;
}
@@ -657,11 +799,11 @@
static bool intel_pt_branch_enable(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
u64 config;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
(config & 1) && !(config & 0x2000))
return false;
}
@@ -670,7 +812,7 @@
static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
unsigned int shift;
u64 config;
@@ -681,7 +823,7 @@
config >>= 1;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, &config))
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config))
return (config & pt->mtc_freq_bits) >> shift;
}
return 0;
@@ -689,7 +831,7 @@
static bool intel_pt_timeless_decoding(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
bool timeless_decoding = true;
u64 config;
@@ -697,9 +839,9 @@
return true;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
+ if (!(evsel->core.attr.sample_type & PERF_SAMPLE_TIME))
return true;
- if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
if (config & pt->tsc_bit)
timeless_decoding = false;
else
@@ -711,11 +853,11 @@
static bool intel_pt_tracing_kernel(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
- !evsel->attr.exclude_kernel)
+ if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
+ !evsel->core.attr.exclude_kernel)
return true;
}
return false;
@@ -723,7 +865,7 @@
static bool intel_pt_have_tsc(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
bool have_tsc = false;
u64 config;
@@ -731,7 +873,7 @@
return false;
evlist__for_each_entry(pt->session->evlist, evsel) {
- if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
if (config & pt->tsc_bit)
have_tsc = true;
else
@@ -739,6 +881,30 @@
}
}
return have_tsc;
+}
+
+static bool intel_pt_sampling_mode(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if ((evsel->core.attr.sample_type & PERF_SAMPLE_AUX) &&
+ evsel->core.attr.aux_sample_size)
+ return true;
+ }
+ return false;
+}
+
+static u64 intel_pt_ctl(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+ u64 config;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->core.attr, &config))
+ return config;
+ }
+ return 0;
}
static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
@@ -750,6 +916,86 @@
return (quot << pt->tc.time_shift) + (rem << pt->tc.time_shift) /
pt->tc.time_mult;
}
+
+static struct ip_callchain *intel_pt_alloc_chain(struct intel_pt *pt)
+{
+ size_t sz = sizeof(struct ip_callchain);
+
+ /* Add 1 to callchain_sz for callchain context */
+ sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
+ return zalloc(sz);
+}
+
+static int intel_pt_callchain_init(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+ evsel->synth_sample_type |= PERF_SAMPLE_CALLCHAIN;
+ }
+
+ pt->chain = intel_pt_alloc_chain(pt);
+ if (!pt->chain)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void intel_pt_add_callchain(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct thread *thread = machine__findnew_thread(pt->machine,
+ sample->pid,
+ sample->tid);
+
+ thread_stack__sample_late(thread, sample->cpu, pt->chain,
+ pt->synth_opts.callchain_sz + 1, sample->ip,
+ pt->kernel_start);
+
+ sample->callchain = pt->chain;
+}
+
+static struct branch_stack *intel_pt_alloc_br_stack(unsigned int entry_cnt)
+{
+ size_t sz = sizeof(struct branch_stack);
+
+ sz += entry_cnt * sizeof(struct branch_entry);
+ return zalloc(sz);
+}
+
+static int intel_pt_br_stack_init(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
+ evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
+ }
+
+ pt->br_stack = intel_pt_alloc_br_stack(pt->br_stack_sz);
+ if (!pt->br_stack)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void intel_pt_add_br_stack(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct thread *thread = machine__findnew_thread(pt->machine,
+ sample->pid,
+ sample->tid);
+
+ thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
+ pt->br_stack_sz, sample->ip,
+ pt->kernel_start);
+
+ sample->branch_stack = pt->br_stack;
+}
+
+/* INTEL_PT_LBR_0, INTEL_PT_LBR_1 and INTEL_PT_LBR_2 */
+#define LBRS_MAX (INTEL_PT_BLK_ITEM_ID_CNT * 3U)
static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
unsigned int queue_nr)
@@ -763,25 +1009,16 @@
return NULL;
if (pt->synth_opts.callchain) {
- size_t sz = sizeof(struct ip_callchain);
-
- /* Add 1 to callchain_sz for callchain context */
- sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
- ptq->chain = zalloc(sz);
+ ptq->chain = intel_pt_alloc_chain(pt);
if (!ptq->chain)
goto out_free;
}
- if (pt->synth_opts.last_branch) {
- size_t sz = sizeof(struct branch_stack);
+ if (pt->synth_opts.last_branch || pt->synth_opts.other_events) {
+ unsigned int entry_cnt = max(LBRS_MAX, pt->br_stack_sz);
- sz += pt->synth_opts.last_branch_sz *
- sizeof(struct branch_entry);
- ptq->last_branch = zalloc(sz);
+ ptq->last_branch = intel_pt_alloc_br_stack(entry_cnt);
if (!ptq->last_branch)
- goto out_free;
- ptq->last_branch_rb = zalloc(sz);
- if (!ptq->last_branch_rb)
goto out_free;
}
@@ -799,13 +1036,16 @@
params.get_trace = intel_pt_get_trace;
params.walk_insn = intel_pt_walk_next_insn;
+ params.lookahead = intel_pt_lookahead;
params.data = ptq;
params.return_compression = intel_pt_return_compression(pt);
params.branch_enable = intel_pt_branch_enable(pt);
+ params.ctl = intel_pt_ctl(pt);
params.max_non_turbo_ratio = pt->max_non_turbo_ratio;
params.mtc_period = intel_pt_mtc_period(pt);
params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n;
params.tsc_ctc_ratio_d = pt->tsc_ctc_ratio_d;
+ params.quick = pt->synth_opts.quick;
if (pt->filts.cnt > 0)
params.pgd_ip = intel_pt_pgd_ip;
@@ -850,7 +1090,6 @@
out_free:
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
return NULL;
@@ -866,7 +1105,6 @@
intel_pt_decoder_free(ptq->decoder);
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
}
@@ -918,6 +1156,28 @@
ptq->insn_len = ptq->state->insn_len;
memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
}
+
+ if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+ ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+ if (ptq->state->type & INTEL_PT_TRACE_END)
+ ptq->flags |= PERF_IP_FLAG_TRACE_END;
+}
+
+static void intel_pt_setup_time_range(struct intel_pt *pt,
+ struct intel_pt_queue *ptq)
+{
+ if (!pt->range_cnt)
+ return;
+
+ ptq->sel_timestamp = pt->time_ranges[0].start;
+ ptq->sel_idx = 0;
+
+ if (ptq->sel_timestamp) {
+ ptq->sel_start = true;
+ } else {
+ ptq->sel_timestamp = pt->time_ranges[0].end;
+ ptq->sel_start = false;
+ }
}
static int intel_pt_setup_queue(struct intel_pt *pt,
@@ -939,11 +1199,15 @@
ptq->cpu = queue->cpu;
ptq->tid = queue->tid;
+ ptq->cbr_seen = UINT_MAX;
+
if (pt->sampling_mode && !pt->snapshot_mode &&
pt->timeless_decoding)
ptq->step_through_buffers = true;
ptq->sync_switch = pt->sync_switch;
+
+ intel_pt_setup_time_range(pt, ptq);
}
if (!ptq->on_heap &&
@@ -958,6 +1222,14 @@
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);
+
+ if (ptq->sel_start && ptq->sel_timestamp) {
+ ret = intel_pt_fast_forward(ptq->decoder,
+ ptq->sel_timestamp);
+ if (ret)
+ return ret;
+ }
+
while (1) {
state = intel_pt_decode(ptq->decoder);
if (state->err) {
@@ -977,6 +1249,9 @@
queue_nr, ptq->timestamp);
ptq->state = state;
ptq->have_sample = true;
+ if (ptq->sel_start && ptq->sel_timestamp &&
+ ptq->timestamp < ptq->sel_timestamp)
+ ptq->have_sample = false;
intel_pt_sample_flags(ptq);
ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
if (ret)
@@ -1000,62 +1275,35 @@
return 0;
}
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
- struct branch_stack *bs_src = ptq->last_branch_rb;
- struct branch_stack *bs_dst = ptq->last_branch;
- size_t nr = 0;
-
- bs_dst->nr = bs_src->nr;
-
- if (!bs_src->nr)
- return;
-
- nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
- memcpy(&bs_dst->entries[0],
- &bs_src->entries[ptq->last_branch_pos],
- sizeof(struct branch_entry) * nr);
-
- if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
- memcpy(&bs_dst->entries[nr],
- &bs_src->entries[0],
- sizeof(struct branch_entry) * ptq->last_branch_pos);
- }
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
- ptq->last_branch_pos = 0;
- ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
- const struct intel_pt_state *state = ptq->state;
- struct branch_stack *bs = ptq->last_branch_rb;
- struct branch_entry *be;
-
- if (!ptq->last_branch_pos)
- ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
- ptq->last_branch_pos -= 1;
-
- be = &bs->entries[ptq->last_branch_pos];
- be->from = state->from_ip;
- be->to = state->to_ip;
- be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
- be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
- /* No support for mispredict */
- be->flags.mispred = ptq->pt->mispred_all;
-
- if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
- bs->nr += 1;
-}
-
static inline bool intel_pt_skip_event(struct intel_pt *pt)
{
return pt->synth_opts.initial_skip &&
pt->num_events++ < pt->synth_opts.initial_skip;
+}
+
+/*
+ * Cannot count CBR as skipped because it won't go away until cbr == cbr_seen.
+ * Also ensure CBR is first non-skipped event by allowing for 4 more samples
+ * from this decoder state.
+ */
+static inline bool intel_pt_skip_cbr_event(struct intel_pt *pt)
+{
+ return pt->synth_opts.initial_skip &&
+ pt->num_events + 4 < pt->synth_opts.initial_skip;
+}
+
+static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
+ union perf_event *event,
+ struct perf_sample *sample)
+{
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ sample->pid = ptq->pid;
+ sample->tid = ptq->tid;
+ sample->cpu = ptq->cpu;
+ sample->insn_len = ptq->insn_len;
+ memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
}
static void intel_pt_prep_b_sample(struct intel_pt *pt,
@@ -1063,23 +1311,18 @@
union perf_event *event,
struct perf_sample *sample)
{
+ intel_pt_prep_a_sample(ptq, event, sample);
+
if (!pt->timeless_decoding)
sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
sample->ip = ptq->state->from_ip;
sample->cpumode = intel_pt_cpumode(pt, sample->ip);
- sample->pid = ptq->pid;
- sample->tid = ptq->tid;
sample->addr = ptq->state->to_ip;
sample->period = 1;
- sample->cpu = ptq->cpu;
sample->flags = ptq->flags;
- sample->insn_len = ptq->insn_len;
- memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
- event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = sample->cpumode;
- event->sample.header.size = sizeof(struct perf_event_header);
}
static int intel_pt_inject_event(union perf_event *event,
@@ -1099,9 +1342,9 @@
return intel_pt_inject_event(event, sample, type);
}
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
- union perf_event *event,
- struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+ union perf_event *event,
+ struct perf_sample *sample, u64 type)
{
int ret;
@@ -1123,6 +1366,7 @@
struct perf_sample sample = { .ip = 0, };
struct dummy_branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries;
} dummy_bs;
@@ -1144,6 +1388,7 @@
if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
+ .hw_idx = -1ULL,
.entries = {
.from = sample.ip,
.to = sample.addr,
@@ -1152,8 +1397,16 @@
sample.branch_stack = (struct branch_stack *)&dummy_bs;
}
- return intel_pt_deliver_synth_b_event(pt, event, &sample,
- pt->branches_sample_type);
+ if (ptq->state->flags & INTEL_PT_SAMPLE_IPC)
+ sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt;
+ if (sample.cyc_cnt) {
+ sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt;
+ ptq->last_br_insn_cnt = ptq->ipc_insn_cnt;
+ ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
+ }
+
+ return intel_pt_deliver_synth_event(pt, event, &sample,
+ pt->branches_sample_type);
}
static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1164,32 +1417,17 @@
intel_pt_prep_b_sample(pt, ptq, event, sample);
if (pt->synth_opts.callchain) {
- thread_stack__sample(ptq->thread, ptq->chain,
+ thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
pt->synth_opts.callchain_sz + 1,
sample->ip, pt->kernel_start);
sample->callchain = ptq->chain;
}
if (pt->synth_opts.last_branch) {
- intel_pt_copy_last_branch_rb(ptq);
+ thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+ pt->br_stack_sz);
sample->branch_stack = ptq->last_branch;
}
-}
-
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
- struct intel_pt_queue *ptq,
- union perf_event *event,
- struct perf_sample *sample,
- u64 type)
-{
- int ret;
-
- ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
- if (pt->synth_opts.last_branch)
- intel_pt_reset_last_branch_rb(ptq);
-
- return ret;
}
static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
@@ -1205,11 +1443,22 @@
sample.id = ptq->pt->instructions_id;
sample.stream_id = ptq->pt->instructions_id;
- sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
+ if (pt->synth_opts.quick)
+ sample.period = 1;
+ else
+ sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
+
+ if (ptq->state->flags & INTEL_PT_SAMPLE_IPC)
+ sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt;
+ if (sample.cyc_cnt) {
+ sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt;
+ ptq->last_in_insn_cnt = ptq->ipc_insn_cnt;
+ ptq->last_in_cyc_cnt = ptq->ipc_cyc_cnt;
+ }
ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->instructions_sample_type);
}
@@ -1227,7 +1476,7 @@
sample.id = ptq->pt->transactions_id;
sample.stream_id = ptq->pt->transactions_id;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->transactions_sample_type);
}
@@ -1268,7 +1517,7 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->ptwrites_sample_type);
}
@@ -1280,8 +1529,10 @@
struct perf_synth_intel_cbr raw;
u32 flags;
- if (intel_pt_skip_event(pt))
+ if (intel_pt_skip_cbr_event(pt))
return 0;
+
+ ptq->cbr_seen = ptq->state->cbr;
intel_pt_prep_p_sample(pt, ptq, event, &sample);
@@ -1296,7 +1547,7 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1321,7 +1572,7 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1346,7 +1597,7 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1371,7 +1622,7 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1396,21 +1647,277 @@
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
+/*
+ * PEBS gp_regs array indexes plus 1 so that 0 means not present. Refer
+ * intel_pt_add_gp_regs().
+ */
+static const int pebs_gp_regs[] = {
+ [PERF_REG_X86_FLAGS] = 1,
+ [PERF_REG_X86_IP] = 2,
+ [PERF_REG_X86_AX] = 3,
+ [PERF_REG_X86_CX] = 4,
+ [PERF_REG_X86_DX] = 5,
+ [PERF_REG_X86_BX] = 6,
+ [PERF_REG_X86_SP] = 7,
+ [PERF_REG_X86_BP] = 8,
+ [PERF_REG_X86_SI] = 9,
+ [PERF_REG_X86_DI] = 10,
+ [PERF_REG_X86_R8] = 11,
+ [PERF_REG_X86_R9] = 12,
+ [PERF_REG_X86_R10] = 13,
+ [PERF_REG_X86_R11] = 14,
+ [PERF_REG_X86_R12] = 15,
+ [PERF_REG_X86_R13] = 16,
+ [PERF_REG_X86_R14] = 17,
+ [PERF_REG_X86_R15] = 18,
+};
+
+static u64 *intel_pt_add_gp_regs(struct regs_dump *intr_regs, u64 *pos,
+ const struct intel_pt_blk_items *items,
+ u64 regs_mask)
+{
+ const u64 *gp_regs = items->val[INTEL_PT_GP_REGS_POS];
+ u32 mask = items->mask[INTEL_PT_GP_REGS_POS];
+ u32 bit;
+ int i;
+
+ for (i = 0, bit = 1; i < PERF_REG_X86_64_MAX; i++, bit <<= 1) {
+ /* Get the PEBS gp_regs array index */
+ int n = pebs_gp_regs[i] - 1;
+
+ if (n < 0)
+ continue;
+ /*
+ * Add only registers that were requested (i.e. 'regs_mask') and
+ * that were provided (i.e. 'mask'), and update the resulting
+ * mask (i.e. 'intr_regs->mask') accordingly.
+ */
+ if (mask & 1 << n && regs_mask & bit) {
+ intr_regs->mask |= bit;
+ *pos++ = gp_regs[n];
+ }
+ }
+
+ return pos;
+}
+
+#ifndef PERF_REG_X86_XMM0
+#define PERF_REG_X86_XMM0 32
+#endif
+
+static void intel_pt_add_xmm(struct regs_dump *intr_regs, u64 *pos,
+ const struct intel_pt_blk_items *items,
+ u64 regs_mask)
+{
+ u32 mask = items->has_xmm & (regs_mask >> PERF_REG_X86_XMM0);
+ const u64 *xmm = items->xmm;
+
+ /*
+ * If there are any XMM registers, then there should be all of them.
+ * Nevertheless, follow the logic to add only registers that were
+ * requested (i.e. 'regs_mask') and that were provided (i.e. 'mask'),
+ * and update the resulting mask (i.e. 'intr_regs->mask') accordingly.
+ */
+ intr_regs->mask |= (u64)mask << PERF_REG_X86_XMM0;
+
+ for (; mask; mask >>= 1, xmm++) {
+ if (mask & 1)
+ *pos++ = *xmm;
+ }
+}
+
+#define LBR_INFO_MISPRED (1ULL << 63)
+#define LBR_INFO_IN_TX (1ULL << 62)
+#define LBR_INFO_ABORT (1ULL << 61)
+#define LBR_INFO_CYCLES 0xffff
+
+/* Refer kernel's intel_pmu_store_pebs_lbrs() */
+static u64 intel_pt_lbr_flags(u64 info)
+{
+ union {
+ struct branch_flags flags;
+ u64 result;
+ } u;
+
+ u.result = 0;
+ u.flags.mispred = !!(info & LBR_INFO_MISPRED);
+ u.flags.predicted = !(info & LBR_INFO_MISPRED);
+ u.flags.in_tx = !!(info & LBR_INFO_IN_TX);
+ u.flags.abort = !!(info & LBR_INFO_ABORT);
+ u.flags.cycles = info & LBR_INFO_CYCLES;
+
+ return u.result;
+}
+
+static void intel_pt_add_lbrs(struct branch_stack *br_stack,
+ const struct intel_pt_blk_items *items)
+{
+ u64 *to;
+ int i;
+
+ br_stack->nr = 0;
+
+ to = &br_stack->entries[0].from;
+
+ for (i = INTEL_PT_LBR_0_POS; i <= INTEL_PT_LBR_2_POS; i++) {
+ u32 mask = items->mask[i];
+ const u64 *from = items->val[i];
+
+ for (; mask; mask >>= 3, from += 3) {
+ if ((mask & 7) == 7) {
+ *to++ = from[0];
+ *to++ = from[1];
+ *to++ = intel_pt_lbr_flags(from[2]);
+ br_stack->nr += 1;
+ }
+ }
+ }
+}
+
+static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
+{
+ const struct intel_pt_blk_items *items = &ptq->state->items;
+ struct perf_sample sample = { .ip = 0, };
+ union perf_event *event = ptq->event_buf;
+ struct intel_pt *pt = ptq->pt;
+ struct evsel *evsel = pt->pebs_evsel;
+ u64 sample_type = evsel->core.attr.sample_type;
+ u64 id = evsel->core.id[0];
+ u8 cpumode;
+ u64 regs[8 * sizeof(sample.intr_regs.mask)];
+
+ if (intel_pt_skip_event(pt))
+ return 0;
+
+ intel_pt_prep_a_sample(ptq, event, &sample);
+
+ sample.id = id;
+ sample.stream_id = id;
+
+ if (!evsel->core.attr.freq)
+ sample.period = evsel->core.attr.sample_period;
+
+ /* No support for non-zero CS base */
+ if (items->has_ip)
+ sample.ip = items->ip;
+ else if (items->has_rip)
+ sample.ip = items->rip;
+ else
+ sample.ip = ptq->state->from_ip;
+
+ /* No support for guest mode at this time */
+ cpumode = sample.ip < ptq->pt->kernel_start ?
+ PERF_RECORD_MISC_USER :
+ PERF_RECORD_MISC_KERNEL;
+
+ event->sample.header.misc = cpumode | PERF_RECORD_MISC_EXACT_IP;
+
+ sample.cpumode = cpumode;
+
+ if (sample_type & PERF_SAMPLE_TIME) {
+ u64 timestamp = 0;
+
+ if (items->has_timestamp)
+ timestamp = items->timestamp;
+ else if (!pt->timeless_decoding)
+ timestamp = ptq->timestamp;
+ if (timestamp)
+ sample.time = tsc_to_perf_time(timestamp, &pt->tc);
+ }
+
+ if (sample_type & PERF_SAMPLE_CALLCHAIN &&
+ pt->synth_opts.callchain) {
+ thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
+ pt->synth_opts.callchain_sz, sample.ip,
+ pt->kernel_start);
+ sample.callchain = ptq->chain;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR &&
+ (items->mask[INTEL_PT_GP_REGS_POS] ||
+ items->mask[INTEL_PT_XMM_POS])) {
+ u64 regs_mask = evsel->core.attr.sample_regs_intr;
+ u64 *pos;
+
+ sample.intr_regs.abi = items->is_32_bit ?
+ PERF_SAMPLE_REGS_ABI_32 :
+ PERF_SAMPLE_REGS_ABI_64;
+ sample.intr_regs.regs = regs;
+
+ pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask);
+
+ intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
+ }
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ if (items->mask[INTEL_PT_LBR_0_POS] ||
+ items->mask[INTEL_PT_LBR_1_POS] ||
+ items->mask[INTEL_PT_LBR_2_POS]) {
+ intel_pt_add_lbrs(ptq->last_branch, items);
+ } else if (pt->synth_opts.last_branch) {
+ thread_stack__br_sample(ptq->thread, ptq->cpu,
+ ptq->last_branch,
+ pt->br_stack_sz);
+ } else {
+ ptq->last_branch->nr = 0;
+ }
+ sample.branch_stack = ptq->last_branch;
+ }
+
+ if (sample_type & PERF_SAMPLE_ADDR && items->has_mem_access_address)
+ sample.addr = items->mem_access_address;
+
+ if (sample_type & PERF_SAMPLE_WEIGHT) {
+ /*
+ * Refer kernel's setup_pebs_adaptive_sample_data() and
+ * intel_hsw_weight().
+ */
+ if (items->has_mem_access_latency)
+ sample.weight = items->mem_access_latency;
+ if (!sample.weight && items->has_tsx_aux_info) {
+ /* Cycles last block */
+ sample.weight = (u32)items->tsx_aux_info;
+ }
+ }
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
+ u64 ax = items->has_rax ? items->rax : 0;
+ /* Refer kernel's intel_hsw_transaction() */
+ u64 txn = (u8)(items->tsx_aux_info >> 32);
+
+ /* For RTM XABORTs also log the abort code from AX */
+ if (txn & PERF_TXN_TRANSACTION && ax & 1)
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ sample.transaction = txn;
+ }
+
+ return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+}
+
static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
- pid_t pid, pid_t tid, u64 ip)
+ pid_t pid, pid_t tid, u64 ip, u64 timestamp)
{
union perf_event event;
char msg[MAX_AUXTRACE_ERROR_MSG];
int err;
+ if (pt->synth_opts.error_minus_flags) {
+ if (code == INTEL_PT_ERR_OVR &&
+ pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_OVERFLOW)
+ return 0;
+ if (code == INTEL_PT_ERR_LOST &&
+ pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_DATA_LOST)
+ return 0;
+ }
+
intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
- code, cpu, pid, tid, ip, msg);
+ code, cpu, pid, tid, ip, msg, timestamp);
err = perf_session__deliver_synth_event(pt->session, &event, NULL);
if (err)
@@ -1418,6 +1925,18 @@
err);
return err;
+}
+
+static int intel_ptq_synth_error(struct intel_pt_queue *ptq,
+ const struct intel_pt_state *state)
+{
+ struct intel_pt *pt = ptq->pt;
+ u64 tm = ptq->timestamp;
+
+ tm = pt->timeless_decoding ? 0 : tsc_to_perf_time(tm, &pt->tc);
+
+ return intel_pt_synth_error(pt, state->err, ptq->cpu, ptq->pid,
+ ptq->tid, state->from_ip, tm);
}
static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
@@ -1452,8 +1971,7 @@
}
#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \
- INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \
- INTEL_PT_CBR_CHG)
+ INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT)
static int intel_pt_sample(struct intel_pt_queue *ptq)
{
@@ -1466,31 +1984,46 @@
ptq->have_sample = false;
- if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) {
- if (state->type & INTEL_PT_CBR_CHG) {
+ ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt;
+ ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt;
+
+ /*
+ * Do PEBS first to allow for the possibility that the PEBS timestamp
+ * precedes the current timestamp.
+ */
+ if (pt->sample_pebs && state->type & INTEL_PT_BLK_ITEMS) {
+ err = intel_pt_synth_pebs_sample(ptq);
+ if (err)
+ return err;
+ }
+
+ if (pt->sample_pwr_events) {
+ if (ptq->state->cbr != ptq->cbr_seen) {
err = intel_pt_synth_cbr_sample(ptq);
if (err)
return err;
}
- if (state->type & INTEL_PT_MWAIT_OP) {
- err = intel_pt_synth_mwait_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_PWR_ENTRY) {
- err = intel_pt_synth_pwre_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_EX_STOP) {
- err = intel_pt_synth_exstop_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_PWR_EXIT) {
- err = intel_pt_synth_pwrx_sample(ptq);
- if (err)
- return err;
+ if (state->type & INTEL_PT_PWR_EVT) {
+ if (state->type & INTEL_PT_MWAIT_OP) {
+ err = intel_pt_synth_mwait_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_PWR_ENTRY) {
+ err = intel_pt_synth_pwre_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_EX_STOP) {
+ err = intel_pt_synth_exstop_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_PWR_EXIT) {
+ err = intel_pt_synth_pwrx_sample(ptq);
+ if (err)
+ return err;
+ }
}
}
@@ -1515,21 +2048,21 @@
if (!(state->type & INTEL_PT_BRANCH))
return 0;
- if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
- 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->use_thread_stack) {
+ thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+ state->from_ip, state->to_ip, ptq->insn_len,
+ state->trace_nr, pt->callstack,
+ pt->br_stack_sz_plus,
+ pt->mispred_all);
+ } else {
+ thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+ }
if (pt->sample_branches) {
err = intel_pt_synth_branch_sample(ptq);
if (err)
return err;
}
-
- if (pt->synth_opts.last_branch)
- intel_pt_update_last_branch_rb(ptq);
if (!ptq->sync_switch)
return 0;
@@ -1628,10 +2161,83 @@
}
}
+/*
+ * To filter against time ranges, it is only necessary to look at the next start
+ * or end time.
+ */
+static bool intel_pt_next_time(struct intel_pt_queue *ptq)
+{
+ struct intel_pt *pt = ptq->pt;
+
+ if (ptq->sel_start) {
+ /* Next time is an end time */
+ ptq->sel_start = false;
+ ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].end;
+ return true;
+ } else if (ptq->sel_idx + 1 < pt->range_cnt) {
+ /* Next time is a start time */
+ ptq->sel_start = true;
+ ptq->sel_idx += 1;
+ ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].start;
+ return true;
+ }
+
+ /* No next time */
+ return false;
+}
+
+static int intel_pt_time_filter(struct intel_pt_queue *ptq, u64 *ff_timestamp)
+{
+ int err;
+
+ while (1) {
+ if (ptq->sel_start) {
+ if (ptq->timestamp >= ptq->sel_timestamp) {
+ /* After start time, so consider next time */
+ intel_pt_next_time(ptq);
+ if (!ptq->sel_timestamp) {
+ /* No end time */
+ return 0;
+ }
+ /* Check against end time */
+ continue;
+ }
+ /* Before start time, so fast forward */
+ ptq->have_sample = false;
+ if (ptq->sel_timestamp > *ff_timestamp) {
+ if (ptq->sync_switch) {
+ intel_pt_next_tid(ptq->pt, ptq);
+ ptq->switch_state = INTEL_PT_SS_UNKNOWN;
+ }
+ *ff_timestamp = ptq->sel_timestamp;
+ err = intel_pt_fast_forward(ptq->decoder,
+ ptq->sel_timestamp);
+ if (err)
+ return err;
+ }
+ return 0;
+ } else if (ptq->timestamp > ptq->sel_timestamp) {
+ /* After end time, so consider next time */
+ if (!intel_pt_next_time(ptq)) {
+ /* No next time range, so stop decoding */
+ ptq->have_sample = false;
+ ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
+ return 1;
+ }
+ /* Check against next start time */
+ continue;
+ } else {
+ /* Before end time */
+ return 0;
+ }
+ }
+}
+
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;
+ u64 ff_timestamp = 0;
int err;
if (!pt->kernel_start) {
@@ -1665,11 +2271,9 @@
ptq->sync_switch = false;
intel_pt_next_tid(pt, ptq);
}
+ ptq->timestamp = state->est_timestamp;
if (pt->synth_opts.errors) {
- err = intel_pt_synth_error(pt, state->err,
- ptq->cpu, ptq->pid,
- ptq->tid,
- state->from_ip);
+ err = intel_ptq_synth_error(ptq, state);
if (err)
return err;
}
@@ -1697,6 +2301,12 @@
ptq->timestamp = state->est_timestamp;
} else if (state->timestamp > ptq->timestamp) {
ptq->timestamp = state->timestamp;
+ }
+
+ if (ptq->sel_timestamp) {
+ err = intel_pt_time_filter(ptq, &ff_timestamp);
+ if (err)
+ return err;
}
if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
@@ -1791,10 +2401,60 @@
return 0;
}
+static void intel_pt_sample_set_pid_tid_cpu(struct intel_pt_queue *ptq,
+ struct auxtrace_queue *queue,
+ struct perf_sample *sample)
+{
+ struct machine *m = ptq->pt->machine;
+
+ ptq->pid = sample->pid;
+ ptq->tid = sample->tid;
+ ptq->cpu = queue->cpu;
+
+ intel_pt_log("queue %u cpu %d pid %d tid %d\n",
+ ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+
+ thread__zput(ptq->thread);
+
+ if (ptq->tid == -1)
+ return;
+
+ if (ptq->pid == -1) {
+ ptq->thread = machine__find_thread(m, -1, ptq->tid);
+ if (ptq->thread)
+ ptq->pid = ptq->thread->pid_;
+ return;
+ }
+
+ ptq->thread = machine__findnew_thread(m, ptq->pid, ptq->tid);
+}
+
+static int intel_pt_process_timeless_sample(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct auxtrace_queue *queue;
+ struct intel_pt_queue *ptq;
+ u64 ts = 0;
+
+ queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session);
+ if (!queue)
+ return -EINVAL;
+
+ ptq = queue->priv;
+ if (!ptq)
+ return 0;
+
+ ptq->stop = false;
+ ptq->time = sample->time;
+ intel_pt_sample_set_pid_tid_cpu(ptq, queue, sample);
+ intel_pt_run_decoder(ptq, &ts);
+ return 0;
+}
+
static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
{
return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
- sample->pid, sample->tid, 0);
+ sample->pid, sample->tid, 0, sample->time);
}
static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
@@ -1840,7 +2500,6 @@
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:
@@ -1860,12 +2519,13 @@
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;
}
+
+ ptq->next_tid = -1;
return 1;
}
@@ -1873,7 +2533,7 @@
static int intel_pt_process_switch(struct intel_pt *pt,
struct perf_sample *sample)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
pid_t tid;
int cpu, ret;
@@ -1881,7 +2541,7 @@
if (evsel != pt->switch_evsel)
return 0;
- tid = perf_evsel__intval(evsel, sample, "next_pid");
+ tid = evsel__intval(evsel, sample, "next_pid");
cpu = sample->cpu;
intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
@@ -1895,6 +2555,44 @@
return machine__set_current_tid(pt->machine, cpu, -1, tid);
}
+static int intel_pt_context_switch_in(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ pid_t pid = sample->pid;
+ pid_t tid = sample->tid;
+ int cpu = sample->cpu;
+
+ if (pt->sync_switch) {
+ struct intel_pt_queue *ptq;
+
+ ptq = intel_pt_cpu_to_ptq(pt, cpu);
+ if (ptq && ptq->sync_switch) {
+ ptq->next_tid = -1;
+ switch (ptq->switch_state) {
+ case INTEL_PT_SS_NOT_TRACING:
+ case INTEL_PT_SS_UNKNOWN:
+ case INTEL_PT_SS_TRACING:
+ break;
+ case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
+ case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+ ptq->switch_state = INTEL_PT_SS_TRACING;
+ break;
+ default:
+ break;
+ }
+ }
+ }
+
+ /*
+ * If the current tid has not been updated yet, ensure it is now that
+ * a "switch in" event has occurred.
+ */
+ if (machine__get_current_tid(pt->machine, cpu) == tid)
+ return 0;
+
+ return machine__set_current_tid(pt->machine, cpu, pid, tid);
+}
+
static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
struct perf_sample *sample)
{
@@ -1906,7 +2604,7 @@
if (pt->have_sched_switch == 3) {
if (!out)
- return 0;
+ return intel_pt_context_switch_in(pt, sample);
if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
pr_err("Expecting CPU-wide context switch event\n");
return -EINVAL;
@@ -1922,10 +2620,6 @@
if (tid == -1)
intel_pt_log("context_switch event has no tid\n");
-
- intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
- cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time,
- &pt->tc));
ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
if (ret <= 0)
@@ -1949,6 +2643,67 @@
return machine__set_current_tid(pt->machine, sample->cpu,
event->itrace_start.pid,
event->itrace_start.tid);
+}
+
+static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr,
+ struct addr_location *al)
+{
+ if (!al->map || addr < al->map->start || addr >= al->map->end) {
+ if (!thread__find_map(thread, cpumode, addr, al))
+ return -1;
+ }
+
+ return 0;
+}
+
+/* Invalidate all instruction cache entries that overlap the text poke */
+static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event)
+{
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ u64 addr = event->text_poke.addr + event->text_poke.new_len - 1;
+ /* Assume text poke begins in a basic block no more than 4096 bytes */
+ int cnt = 4096 + event->text_poke.new_len;
+ struct thread *thread = pt->unknown_thread;
+ struct addr_location al = { .map = NULL };
+ struct machine *machine = pt->machine;
+ struct intel_pt_cache_entry *e;
+ u64 offset;
+
+ if (!event->text_poke.new_len)
+ return 0;
+
+ for (; cnt; cnt--, addr--) {
+ if (intel_pt_find_map(thread, cpumode, addr, &al)) {
+ if (addr < event->text_poke.addr)
+ return 0;
+ continue;
+ }
+
+ if (!al.map->dso || !al.map->dso->auxtrace_cache)
+ continue;
+
+ offset = al.map->map_ip(al.map, addr);
+
+ e = intel_pt_cache_lookup(al.map->dso, machine, offset);
+ if (!e)
+ continue;
+
+ if (addr + e->byte_cnt + e->length <= event->text_poke.addr) {
+ /*
+ * No overlap. Working backwards there cannot be another
+ * basic block that overlaps the text poke if there is a
+ * branch instruction before the text poke address.
+ */
+ if (e->branch != INTEL_PT_BR_NO_BRANCH)
+ return 0;
+ } else {
+ intel_pt_cache_invalidate(al.map->dso, machine, offset);
+ intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n",
+ al.map->dso->long_name, addr);
+ }
+ }
+
+ return 0;
}
static int intel_pt_process_event(struct perf_session *session,
@@ -1981,7 +2736,11 @@
}
if (pt->timeless_decoding) {
- if (event->header.type == PERF_RECORD_EXIT) {
+ if (pt->sampling_mode) {
+ if (sample->aux_sample.size)
+ err = intel_pt_process_timeless_sample(pt,
+ sample);
+ } else if (event->header.type == PERF_RECORD_EXIT) {
err = intel_pt_process_timeless_queues(pt,
event->fork.tid,
sample->time);
@@ -1991,6 +2750,13 @@
}
if (err)
return err;
+
+ if (event->header.type == PERF_RECORD_SAMPLE) {
+ if (pt->synth_opts.add_callchain && !sample->callchain)
+ intel_pt_add_callchain(pt, sample);
+ if (pt->synth_opts.add_last_branch && !sample->branch_stack)
+ intel_pt_add_br_stack(pt, sample);
+ }
if (event->header.type == PERF_RECORD_AUX &&
(event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
@@ -2008,9 +2774,14 @@
event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
err = intel_pt_context_switch(pt, event, sample);
- intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
- perf_event__name(event->header.type), event->header.type,
- sample->cpu, sample->time, timestamp);
+ if (!err && event->header.type == PERF_RECORD_TEXT_POKE)
+ err = intel_pt_text_poke(pt, event);
+
+ if (intel_pt_enable_logging && intel_pt_log_events(pt, sample->time)) {
+ intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+ event->header.type, sample->cpu, sample->time, timestamp);
+ intel_pt_log_event(event);
+ }
return err;
}
@@ -2063,8 +2834,19 @@
session->auxtrace = NULL;
thread__put(pt->unknown_thread);
addr_filters__exit(&pt->filts);
+ zfree(&pt->chain);
zfree(&pt->filter);
+ zfree(&pt->time_ranges);
free(pt);
+}
+
+static bool intel_pt_evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+
+ return evsel->core.attr.type == pt->pmu_type;
}
static int intel_pt_process_auxtrace_event(struct perf_session *session,
@@ -2106,6 +2888,28 @@
return 0;
}
+static int intel_pt_queue_data(struct perf_session *session,
+ struct perf_sample *sample,
+ union perf_event *event, u64 data_offset)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+ u64 timestamp;
+
+ if (event) {
+ return auxtrace_queues__add_event(&pt->queues, session, event,
+ data_offset, NULL);
+ }
+
+ if (sample->time && sample->time != (u64)-1)
+ timestamp = perf_time_to_tsc(sample->time, &pt->tc);
+ else
+ timestamp = 0;
+
+ return auxtrace_queues__add_sample(&pt->queues, session, sample,
+ data_offset, timestamp);
+}
+
struct intel_pt_synth {
struct perf_tool dummy_tool;
struct perf_session *session;
@@ -2144,13 +2948,13 @@
return err;
}
-static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id,
+static void intel_pt_set_event_name(struct evlist *evlist, u64 id,
const char *name)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- if (evsel->id && evsel->id[0] == id) {
+ if (evsel->core.id && evsel->core.id[0] == id) {
if (evsel->name)
zfree(&evsel->name);
evsel->name = strdup(name);
@@ -2159,13 +2963,13 @@
}
}
-static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt,
- struct perf_evlist *evlist)
+static struct evsel *intel_pt_evsel(struct intel_pt *pt,
+ struct evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- if (evsel->attr.type == pt->pmu_type && evsel->ids)
+ if (evsel->core.attr.type == pt->pmu_type && evsel->core.ids)
return evsel;
}
@@ -2175,8 +2979,8 @@
static int intel_pt_synth_events(struct intel_pt *pt,
struct perf_session *session)
{
- struct perf_evlist *evlist = session->evlist;
- struct perf_evsel *evsel = intel_pt_evsel(pt, evlist);
+ struct evlist *evlist = session->evlist;
+ struct evsel *evsel = intel_pt_evsel(pt, evlist);
struct perf_event_attr attr;
u64 id;
int err;
@@ -2189,7 +2993,7 @@
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 = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
PERF_SAMPLE_PERIOD;
if (pt->timeless_decoding)
@@ -2198,15 +3002,15 @@
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;
+ attr.exclude_user = evsel->core.attr.exclude_user;
+ attr.exclude_kernel = evsel->core.attr.exclude_kernel;
+ attr.exclude_hv = evsel->core.attr.exclude_hv;
+ attr.exclude_host = evsel->core.attr.exclude_host;
+ attr.exclude_guest = evsel->core.attr.exclude_guest;
+ attr.sample_id_all = evsel->core.attr.sample_id_all;
+ attr.read_format = evsel->core.attr.read_format;
- id = evsel->id[0] + 1000000000;
+ id = evsel->core.id[0] + 1000000000;
if (!id)
id = 1;
@@ -2226,8 +3030,15 @@
if (pt->synth_opts.callchain)
attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
- if (pt->synth_opts.last_branch)
+ if (pt->synth_opts.last_branch) {
attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+ /*
+ * We don't use the hardware index, but the sample generation
+ * code uses the new format branch_stack with this field,
+ * so the event attributes must indicate that it's present.
+ */
+ attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+ }
if (pt->synth_opts.instructions) {
attr.config = PERF_COUNT_HW_INSTRUCTIONS;
@@ -2288,7 +3099,7 @@
id += 1;
}
- if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) {
+ if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) {
attr.config = PERF_SYNTH_INTEL_MWAIT;
err = intel_pt_synth_event(session, "mwait", &attr, id);
if (err)
@@ -2325,12 +3136,28 @@
return 0;
}
-static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
+static void intel_pt_setup_pebs_events(struct intel_pt *pt)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
+
+ if (!pt->synth_opts.other_events)
+ return;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (evsel->core.attr.aux_output && evsel->core.id) {
+ pt->sample_pebs = true;
+ pt->pebs_evsel = evsel;
+ return;
+ }
+ }
+}
+
+static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
+{
+ struct evsel *evsel;
evlist__for_each_entry_reverse(evlist, evsel) {
- const char *name = perf_evsel__name(evsel);
+ const char *name = evsel__name(evsel);
if (!strcmp(name, "sched:sched_switch"))
return evsel;
@@ -2339,12 +3166,12 @@
return NULL;
}
-static bool intel_pt_find_switch(struct perf_evlist *evlist)
+static bool intel_pt_find_switch(struct evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- if (evsel->attr.context_switch)
+ if (evsel->core.attr.context_switch)
return true;
}
@@ -2361,6 +3188,85 @@
return 0;
}
+/* Find least TSC which converts to ns or later */
+static u64 intel_pt_tsc_start(u64 ns, struct intel_pt *pt)
+{
+ u64 tsc, tm;
+
+ tsc = perf_time_to_tsc(ns, &pt->tc);
+
+ while (1) {
+ tm = tsc_to_perf_time(tsc, &pt->tc);
+ if (tm < ns)
+ break;
+ tsc -= 1;
+ }
+
+ while (tm < ns)
+ tm = tsc_to_perf_time(++tsc, &pt->tc);
+
+ return tsc;
+}
+
+/* Find greatest TSC which converts to ns or earlier */
+static u64 intel_pt_tsc_end(u64 ns, struct intel_pt *pt)
+{
+ u64 tsc, tm;
+
+ tsc = perf_time_to_tsc(ns, &pt->tc);
+
+ while (1) {
+ tm = tsc_to_perf_time(tsc, &pt->tc);
+ if (tm > ns)
+ break;
+ tsc += 1;
+ }
+
+ while (tm > ns)
+ tm = tsc_to_perf_time(--tsc, &pt->tc);
+
+ return tsc;
+}
+
+static int intel_pt_setup_time_ranges(struct intel_pt *pt,
+ struct itrace_synth_opts *opts)
+{
+ struct perf_time_interval *p = opts->ptime_range;
+ int n = opts->range_num;
+ int i;
+
+ if (!n || !p || pt->timeless_decoding)
+ return 0;
+
+ pt->time_ranges = calloc(n, sizeof(struct range));
+ if (!pt->time_ranges)
+ return -ENOMEM;
+
+ pt->range_cnt = n;
+
+ intel_pt_log("%s: %u range(s)\n", __func__, n);
+
+ for (i = 0; i < n; i++) {
+ struct range *r = &pt->time_ranges[i];
+ u64 ts = p[i].start;
+ u64 te = p[i].end;
+
+ /*
+ * Take care to ensure the TSC range matches the perf-time range
+ * when converted back to perf-time.
+ */
+ r->start = ts ? intel_pt_tsc_start(ts, pt) : 0;
+ r->end = te ? intel_pt_tsc_end(te, pt) : 0;
+
+ intel_pt_log("range %d: perf time interval: %"PRIu64" to %"PRIu64"\n",
+ i, ts, te);
+ intel_pt_log("range %d: TSC time interval: %#"PRIx64" to %#"PRIx64"\n",
+ i, r->start, r->end);
+ }
+
+ return 0;
+}
+
static const char * const intel_pt_info_fmts[] = {
[INTEL_PT_PMU_TYPE] = " PMU Type %"PRId64"\n",
[INTEL_PT_TIME_SHIFT] = " Time Shift %"PRIu64"\n",
@@ -2373,6 +3279,7 @@
[INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n",
[INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n",
[INTEL_PT_MTC_BIT] = " MTC bit %#"PRIx64"\n",
+ [INTEL_PT_MTC_FREQ_BITS] = " MTC freq bits %#"PRIx64"\n",
[INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n",
[INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n",
[INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n",
@@ -2380,15 +3287,19 @@
[INTEL_PT_FILTER_STR_LEN] = " Filter string len. %"PRIu64"\n",
};
-static void intel_pt_print_info(u64 *arr, int start, int finish)
+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]);
+ for (i = start; i <= finish; i++) {
+ const char *fmt = intel_pt_info_fmts[i];
+
+ if (fmt)
+ fprintf(stdout, fmt, arr[i]);
+ }
}
static void intel_pt_print_info_str(const char *name, const char *str)
@@ -2399,23 +3310,23 @@
fprintf(stdout, " %-20s%s\n", name, str ? str : "");
}
-static bool intel_pt_has(struct auxtrace_info_event *auxtrace_info, int pos)
+static bool intel_pt_has(struct perf_record_auxtrace_info *auxtrace_info, int pos)
{
return auxtrace_info->header.size >=
- sizeof(struct auxtrace_info_event) + (sizeof(u64) * (pos + 1));
+ sizeof(struct perf_record_auxtrace_info) + (sizeof(u64) * (pos + 1));
}
int intel_pt_process_auxtrace_info(union perf_event *event,
struct perf_session *session)
{
- struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+ struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
struct intel_pt *pt;
void *info_end;
- u64 *info;
+ __u64 *info;
int err;
- if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+ if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
min_sz)
return -EINVAL;
@@ -2513,7 +3424,7 @@
if (pt->timeless_decoding && !pt->tc.time_mult)
pt->tc.time_mult = 1;
pt->have_tsc = intel_pt_have_tsc(pt);
- pt->sampling_mode = false;
+ pt->sampling_mode = intel_pt_sampling_mode(pt);
pt->est_tsc = !pt->timeless_decoding;
pt->unknown_thread = thread__new(999999999, 999999999);
@@ -2533,16 +3444,19 @@
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)) {
+ if (thread__init_maps(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.queue_data = intel_pt_queue_data;
+ pt->auxtrace.dump_auxtrace_sample = intel_pt_dump_sample;
pt->auxtrace.flush_events = intel_pt_flush;
pt->auxtrace.free_events = intel_pt_free_events;
pt->auxtrace.free = intel_pt_free;
+ pt->auxtrace.evsel_is_auxtrace = intel_pt_evsel_is_auxtrace;
session->auxtrace = &pt->auxtrace;
if (dump_trace)
@@ -2562,16 +3476,18 @@
goto err_delete_thread;
}
- if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+ if (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) {
+ itrace_synth_opts__set_default(&pt->synth_opts,
+ session->itrace_synth_opts->default_no_sample);
+ if (!session->itrace_synth_opts->default_no_sample &&
+ !session->itrace_synth_opts->inject) {
pt->synth_opts.branches = false;
pt->synth_opts.callchain = true;
+ pt->synth_opts.add_callchain = true;
}
- if (session->itrace_synth_opts)
- pt->synth_opts.thread_stack =
+ pt->synth_opts.thread_stack =
session->itrace_synth_opts->thread_stack;
}
@@ -2591,6 +3507,10 @@
pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000;
}
+ err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
+ if (err)
+ goto err_delete_thread;
+
if (pt->synth_opts.calls)
pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
PERF_IP_FLAG_TRACE_END;
@@ -2598,19 +3518,64 @@
pt->branches_filter |= PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_TRACE_BEGIN;
- if (pt->synth_opts.callchain && !symbol_conf.use_callchain) {
+ if ((pt->synth_opts.callchain || pt->synth_opts.add_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;
+ pt->synth_opts.add_callchain = false;
}
}
+
+ if (pt->synth_opts.add_callchain) {
+ err = intel_pt_callchain_init(pt);
+ if (err)
+ goto err_delete_thread;
+ }
+
+ if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
+ pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+ pt->br_stack_sz_plus = pt->br_stack_sz;
+ }
+
+ if (pt->synth_opts.add_last_branch) {
+ err = intel_pt_br_stack_init(pt);
+ if (err)
+ goto err_delete_thread;
+ /*
+ * Additional branch stack size to cater for tracing from the
+ * actual sample ip to where the sample time is recorded.
+ * Measured at about 200 branches, but generously set to 1024.
+ * If kernel space is not being traced, then add just 1 for the
+ * branch to kernel space.
+ */
+ if (intel_pt_tracing_kernel(pt))
+ pt->br_stack_sz_plus += 1024;
+ else
+ pt->br_stack_sz_plus += 1;
+ }
+
+ pt->use_thread_stack = pt->synth_opts.callchain ||
+ pt->synth_opts.add_callchain ||
+ pt->synth_opts.thread_stack ||
+ pt->synth_opts.last_branch ||
+ pt->synth_opts.add_last_branch;
+
+ pt->callstack = pt->synth_opts.callchain ||
+ pt->synth_opts.add_callchain ||
+ pt->synth_opts.thread_stack;
err = intel_pt_synth_events(pt, session);
if (err)
goto err_delete_thread;
- err = auxtrace_queues__process_index(&pt->queues, session);
+ intel_pt_setup_pebs_events(pt);
+
+ if (pt->sampling_mode || list_empty(&session->auxtrace_index))
+ err = auxtrace_queue_data(session, true, true);
+ else
+ err = auxtrace_queues__process_index(&pt->queues, session);
if (err)
goto err_delete_thread;
@@ -2623,6 +3588,7 @@
return 0;
err_delete_thread:
+ zfree(&pt->chain);
thread__zput(pt->unknown_thread);
err_free_queues:
intel_pt_log_disable();
@@ -2631,6 +3597,7 @@
err_free:
addr_filters__exit(&pt->filts);
zfree(&pt->filter);
+ zfree(&pt->time_ranges);
free(pt);
return err;
}
--
Gitblit v1.6.2