From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org,
Adrian Hunter <adrian.hunter@intel.com>,
Jiri Olsa <jolsa@redhat.com>,
Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 05/22] perf tools: Fix Intel PT 'instructions' sample period
Date: Wed, 26 Aug 2015 12:57:55 -0300 [thread overview]
Message-ID: <1440604692-26918-6-git-send-email-acme@kernel.org> (raw)
In-Reply-To: <1440604692-26918-1-git-send-email-acme@kernel.org>
From: Adrian Hunter <adrian.hunter@intel.com>
The period on synthesized 'instructions' samples was being set to a
fixed value, whereas the correct value is the number of instructions
since the last sample, which is a value that the decoder can provide.
So do it that way.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1437150840-31811-14-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 3 +++
tools/perf/util/intel-pt-decoder/intel-pt-decoder.h | 1 +
tools/perf/util/intel-pt.c | 5 ++++-
3 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index f8ac462fec1a..56790ea1e88e 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -108,6 +108,7 @@ struct intel_pt_decoder {
uint64_t sign_bits;
uint64_t period;
enum intel_pt_period_type period_type;
+ uint64_t tot_insn_cnt;
uint64_t period_insn_cnt;
uint64_t period_mask;
uint64_t period_ticks;
@@ -559,6 +560,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
err = decoder->walk_insn(intel_pt_insn, &insn_cnt, &decoder->ip, ip,
max_insn_cnt, decoder->data);
+ decoder->tot_insn_cnt += insn_cnt;
decoder->timestamp_insn_cnt += insn_cnt;
decoder->period_insn_cnt += insn_cnt;
@@ -1529,6 +1531,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
decoder->state.timestamp = decoder->timestamp;
decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
decoder->state.cr3 = decoder->cr3;
+ decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
if (err)
decoder->state.from_ip = decoder->ip;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 4c4880230cc9..cbf57044c385 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -58,6 +58,7 @@ struct intel_pt_state {
uint64_t from_ip;
uint64_t to_ip;
uint64_t cr3;
+ uint64_t tot_insn_cnt;
uint64_t timestamp;
uint64_t est_timestamp;
uint64_t trace_nr;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index a5acd2fe2447..3b34a64195ea 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -126,6 +126,7 @@ struct intel_pt_queue {
u64 timestamp;
u32 flags;
u16 insn_len;
+ u64 last_insn_cnt;
};
static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
@@ -920,11 +921,13 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
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.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
sample.cpu = ptq->cpu;
sample.flags = ptq->flags;
sample.insn_len = ptq->insn_len;
+ ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
+
if (pt->synth_opts.callchain) {
thread_stack__sample(ptq->thread, ptq->chain,
pt->synth_opts.callchain_sz, sample.ip);
--
2.1.0
next prev parent reply other threads:[~2015-08-26 16:05 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-26 15:57 [GIT PULL 00/22] perf/core improvements and fixes Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 01/22] perf tools: Fix tarball build broken by pt/bts Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 02/22] perf annotate: Reset the dso find_symbol cache when removing symbols Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 03/22] perf ui tui progress: Implement the ui_progress_ops->finish() method Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 04/22] perf ordered_events: Clear the progress bar at the end of a flush Arnaldo Carvalho de Melo
2015-08-26 15:57 ` Arnaldo Carvalho de Melo [this message]
2015-08-26 15:57 ` [PATCH 06/22] perf tools: Add Intel PT support for PSB periods Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 07/22] perf tools: Add new Intel PT packet definitions Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 08/22] perf tools: Pass Intel PT information for decoding MTC and CYC Arnaldo Carvalho de Melo
2015-08-26 15:57 ` [PATCH 09/22] perf tools: Add Intel PT support for decoding MTC packets Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 10/22] perf tools: Add Intel PT support for using " Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 11/22] perf tools: Add Intel PT support for decoding CYC packets Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 12/22] perf tools: Add Intel PT support for using " Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 13/22] perf tools: Add Intel PT support for decoding TRACESTOP packets Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 14/22] perf tools: Update Intel PT documentation Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 15/22] perf probe: Prevent segfault when reading probe point with absolute address Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 16/22] perf tools: Remove export.h from MANIFEST Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 17/22] tools build: Allow duplicate objects in the object list Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 18/22] perf probe: Fix list result when symbol can't be found Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 19/22] perf probe: Fix list result when address is zero Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 20/22] perf probe: Fix error reported when offset without function Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 21/22] perf probe: Support probing at absolute address Arnaldo Carvalho de Melo
2015-08-26 15:58 ` [PATCH 22/22] tracing/uprobes: Do not print '0x (null)' when offset is 0 Arnaldo Carvalho de Melo
2015-08-28 6:24 ` [GIT PULL 00/22] perf/core improvements and fixes Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1440604692-26918-6-git-send-email-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).