From: Adrian Hunter <adrian.hunter@intel.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
Andi Kleen <ak@linux.intel.com>
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH V2 02/37] perf intel-pt: Improve sample timestamp
Date: Fri, 26 May 2017 11:17:03 +0300 [thread overview]
Message-ID: <1495786658-18063-3-git-send-email-adrian.hunter@intel.com> (raw)
In-Reply-To: <1495786658-18063-1-git-send-email-adrian.hunter@intel.com>
The decoder uses its current timestamp in samples. Usually that is a
timestamp that has already passed, but in some cases it is a timestamp for
a branch that the decoder is walking towards, and consequently hasn't
reached. Improve that situation by using the pkt_state to determine when
to use the current or previous timestamp.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@vger.kernel.org
---
.../perf/util/intel-pt-decoder/intel-pt-decoder.c | 34 ++++++++++++++++++++--
1 file changed, 31 insertions(+), 3 deletions(-)
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 5a9676c6e23f..d5c69e822282 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -64,6 +64,25 @@ enum intel_pt_pkt_state {
INTEL_PT_STATE_FUP_NO_TIP,
};
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+ switch (pkt_state) {
+ case INTEL_PT_STATE_NO_PSB:
+ case INTEL_PT_STATE_NO_IP:
+ case INTEL_PT_STATE_ERR_RESYNC:
+ case INTEL_PT_STATE_IN_SYNC:
+ case INTEL_PT_STATE_TNT:
+ return true;
+ case INTEL_PT_STATE_TIP:
+ case INTEL_PT_STATE_TIP_PGD:
+ case INTEL_PT_STATE_FUP:
+ case INTEL_PT_STATE_FUP_NO_TIP:
+ return false;
+ default:
+ return true;
+ };
+}
+
#ifdef INTEL_PT_STRICT
#define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB
#define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB
@@ -99,6 +118,7 @@ struct intel_pt_decoder {
uint64_t timestamp;
uint64_t tsc_timestamp;
uint64_t ref_timestamp;
+ uint64_t sample_timestamp;
uint64_t ret_addr;
uint64_t ctc_timestamp;
uint64_t ctc_delta;
@@ -139,6 +159,7 @@ struct intel_pt_decoder {
unsigned int fup_tx_flags;
unsigned int tx_flags;
uint64_t timestamp_insn_cnt;
+ uint64_t sample_insn_cnt;
uint64_t stuck_ip;
int no_progress;
int stuck_ip_prd;
@@ -898,6 +919,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
decoder->tot_insn_cnt += insn_cnt;
decoder->timestamp_insn_cnt += insn_cnt;
+ decoder->sample_insn_cnt += insn_cnt;
decoder->period_insn_cnt += insn_cnt;
if (err) {
@@ -2069,7 +2091,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
{
- uint64_t est = decoder->timestamp_insn_cnt << 1;
+ uint64_t est = decoder->sample_insn_cnt << 1;
if (!decoder->cbr || !decoder->max_non_turbo_ratio)
goto out;
@@ -2077,7 +2099,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
est *= decoder->max_non_turbo_ratio;
est /= decoder->cbr;
out:
- return decoder->timestamp + est;
+ return decoder->sample_timestamp + est;
}
const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
@@ -2133,11 +2155,17 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
if (err) {
decoder->state.err = intel_pt_ext_err(err);
decoder->state.from_ip = decoder->ip;
+ decoder->sample_timestamp = decoder->timestamp;
+ decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
} else {
decoder->state.err = 0;
+ if (intel_pt_sample_time(decoder->pkt_state)) {
+ decoder->sample_timestamp = decoder->timestamp;
+ decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+ }
}
- decoder->state.timestamp = decoder->timestamp;
+ decoder->state.timestamp = decoder->sample_timestamp;
decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
decoder->state.cr3 = decoder->cr3;
decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
--
1.9.1
next prev parent reply other threads:[~2017-05-26 8:34 UTC|newest]
Thread overview: 100+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-26 8:17 [PATCH V2 00/37] perf intel-pt: Power events and PTWRITE Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 01/37] perf intel-pt: Move decoder error setting into one condition Adrian Hunter
2017-06-21 18:19 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` Adrian Hunter [this message]
2017-06-21 18:20 ` [tip:perf/core] perf intel-pt: Improve sample timestamp tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 03/37] perf intel-pt: Fix missing stack clear Adrian Hunter
2017-06-21 18:20 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 04/37] perf intel-pt: Ensure IP is zero when state is INTEL_PT_STATE_NO_IP Adrian Hunter
2017-06-21 18:21 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 05/37] perf intel-pt: Fix last_ip usage Adrian Hunter
2017-06-21 18:22 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 06/37] perf intel-pt: Ensure never to set 'last_ip' when packet 'count' is zero Adrian Hunter
2017-06-21 18:22 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 07/37] perf intel-pt: Use FUP always when scanning for an IP Adrian Hunter
2017-06-21 18:23 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 08/37] perf intel-pt: Clear FUP flag on error Adrian Hunter
2017-06-21 18:23 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 09/37] perf intel-pt: Add missing __fallthrough Adrian Hunter
2017-06-21 18:24 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 10/37] perf intel-pt: Allow decoding with branch tracing disabled Adrian Hunter
2017-06-21 18:24 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 11/37] perf intel-pt: Add default config for pass-through branch enable Adrian Hunter
2017-06-21 18:25 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 12/37] perf intel-pt: Add documentation for new config terms Adrian Hunter
2017-06-21 18:25 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 13/37] perf intel-pt: Add decoder support for ptwrite and power event packets Adrian Hunter
2017-06-21 18:26 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 14/37] perf intel-pt: Add reserved byte to CBR packet payload Adrian Hunter
2017-06-21 18:27 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 15/37] perf intel-pt: Add decoder support for CBR events Adrian Hunter
2017-06-21 18:27 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 16/37] perf intel-pt: Remove redundant initial_skip checks Adrian Hunter
2017-06-21 18:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 17/37] perf intel-pt: Fix transactions_sample_type Adrian Hunter
2017-06-21 18:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 18/37] perf tools: Fix message because cpu list option is -C not -c Adrian Hunter
2017-06-21 18:29 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 19/37] perf script: Fix message because field list option is -F not -f Adrian Hunter
2017-06-21 18:29 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 20/37] perf script: Add 'synth' event type for synthesized events Adrian Hunter
2017-06-21 10:17 ` [PATCH V3 " Adrian Hunter
2017-06-21 13:51 ` Arnaldo Carvalho de Melo
2017-06-21 16:41 ` Adrian Hunter
2017-06-21 17:29 ` Arnaldo Carvalho de Melo
2017-06-21 20:20 ` Adrian Hunter
2017-06-22 14:59 ` Arnaldo Carvalho de Melo
2017-07-01 8:50 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 21/37] perf script: Add 'synth' field for synthesized event payloads Adrian Hunter
2017-06-21 10:17 ` [PATCH V3 " Adrian Hunter
2017-07-01 8:51 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 22/37] tools include: Add byte-swapping macros to kernel.h Adrian Hunter
2017-07-01 8:50 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 23/37] perf auxtrace: Add itrace option to output ptwrite events Adrian Hunter
2017-07-01 8:51 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 24/37] perf auxtrace: Add itrace option to output power events Adrian Hunter
2017-07-01 8:51 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 25/37] perf script: Add synthesized Intel PT power and ptwrite events Adrian Hunter
2017-06-28 13:04 ` Arnaldo Carvalho de Melo
2017-06-28 17:40 ` Adrian Hunter
2017-06-28 18:53 ` Arnaldo Carvalho de Melo
2017-06-28 20:21 ` Hunter, Adrian
2017-06-28 20:26 ` Arnaldo Carvalho de Melo
2017-06-29 19:56 ` Adrian Hunter
2017-06-29 20:13 ` Arnaldo Carvalho de Melo
2017-06-30 2:08 ` Arnaldo Carvalho de Melo
2017-06-30 8:51 ` Adrian Hunter
2017-06-30 14:54 ` Arnaldo Carvalho de Melo
2017-06-30 19:37 ` Hunter, Adrian
2017-06-30 8:36 ` [PATCH V3 " Adrian Hunter
2017-07-01 8:52 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 26/37] perf intel-pt: Factor out common code synthesizing event samples Adrian Hunter
2017-07-01 8:52 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 27/37] perf intel-pt: Remove unused instructions_sample_period Adrian Hunter
2017-07-01 8:52 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 28/37] perf intel-pt: Join needlessly wrapped lines Adrian Hunter
2017-07-01 8:53 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 29/37] perf intel-pt: Tidy Intel PT evsel lookup into separate function Adrian Hunter
2017-07-01 8:53 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 30/37] perf intel-pt: Tidy messages into called function intel_pt_synth_event() Adrian Hunter
2017-07-01 8:53 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 31/37] perf intel-pt: Factor out intel_pt_set_event_name() Adrian Hunter
2017-07-01 8:54 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 32/37] perf intel-pt: Move code in intel_pt_synth_events() to simplify attr setting Adrian Hunter
2017-07-01 8:54 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 33/37] perf intel-pt: Synthesize new power and ptwrite events Adrian Hunter
2017-06-30 8:36 ` [PATCH V3 " Adrian Hunter
2017-07-01 8:54 ` [tip:perf/core] perf intel-pt: Synthesize new power and "ptwrite" events tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 34/37] perf intel-pt: Add example script for power events and PTWRITE Adrian Hunter
2017-07-01 8:55 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 35/37] perf intel-pt: Update documentation to include new ptwrite and power events Adrian Hunter
2017-07-01 8:55 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 36/37] perf intel-pt: Do not use TSC packets for calculating CPU cycles to TSC Adrian Hunter
2017-07-01 8:56 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-05-26 8:17 ` [PATCH V2 37/37] perf auxtrace: Add CPU filter support Adrian Hunter
2017-07-01 8:56 ` [tip:perf/core] " tip-bot for Adrian Hunter
2017-06-12 13:04 ` [PATCH V2 00/37] perf intel-pt: Power events and PTWRITE Adrian Hunter
2017-06-12 13:56 ` Arnaldo Carvalho de Melo
2017-06-21 10:20 ` Adrian Hunter
2017-06-21 13:40 ` Arnaldo Carvalho de Melo
2017-06-27 15:27 ` Arnaldo Carvalho de Melo
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=1495786658-18063-3-git-send-email-adrian.hunter@intel.com \
--to=adrian.hunter@intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=linux-kernel@vger.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).