2020-02-03 01:54:42

by Leo Yan

[permalink] [raw]
Subject: [PATCH v3 4/5] perf cs-etm: Optimize copying last branches

If an instruction range packet can generate multiple instruction
samples, these samples share the same last branches; it's not necessary
to copy the same last branches repeatedly for these samples within the
same packet.

This patch moves out the last branches copying from function
cs_etm__synth_instruction_sample(), and execute it prior to generating
instruction samples.

Signed-off-by: Leo Yan <[email protected]>
---
tools/perf/util/cs-etm.c | 22 +++++++++++++++++-----
1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index c5a05f728eac..dbddf1eec2be 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1134,10 +1134,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,

cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);

- if (etm->synth_opts.last_branch) {
- cs_etm__copy_last_branch_rb(etmq, tidq);
+ if (etm->synth_opts.last_branch)
sample.branch_stack = tidq->last_branch;
- }

if (etm->synth_opts.inject) {
ret = cs_etm__inject_event(event, &sample,
@@ -1407,6 +1405,10 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
*/
u64 instrs_over = instrs_executed;

+ /* Prepare last branches for instruction sample */
+ if (etm->synth_opts.last_branch)
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+
/*
* 'head' is the instructions number of the head in the new
* packet, it combines with the tail of previous packet to
@@ -1526,6 +1528,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,

if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+ u64 addr;
+
+ /* Prepare last branches for instruction sample */
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+
/*
* Generate a last branch event for the branches left in the
* circular buffer at the end of the trace.
@@ -1533,7 +1540,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
* Use the address of the end of the last reported execution
* range
*/
- u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+ addr = cs_etm__last_executed_instr(tidq->prev_packet);

err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
@@ -1587,11 +1594,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
*/
if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+ u64 addr;
+
+ /* Prepare last branches for instruction sample */
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+
/*
* Use the address of the end of the last reported execution
* range.
*/
- u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+ addr = cs_etm__last_executed_instr(tidq->prev_packet);

err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
--
2.17.1


2020-02-06 11:55:23

by Mike Leach

[permalink] [raw]
Subject: Re: [PATCH v3 4/5] perf cs-etm: Optimize copying last branches

Reviewed by: Mike Leach <[email protected]>

On Mon, 3 Feb 2020 at 01:53, Leo Yan <[email protected]> wrote:
>
> If an instruction range packet can generate multiple instruction
> samples, these samples share the same last branches; it's not necessary
> to copy the same last branches repeatedly for these samples within the
> same packet.
>
> This patch moves out the last branches copying from function
> cs_etm__synth_instruction_sample(), and execute it prior to generating
> instruction samples.
>
> Signed-off-by: Leo Yan <[email protected]>
> ---
> tools/perf/util/cs-etm.c | 22 +++++++++++++++++-----
> 1 file changed, 17 insertions(+), 5 deletions(-)
>
> diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
> index c5a05f728eac..dbddf1eec2be 100644
> --- a/tools/perf/util/cs-etm.c
> +++ b/tools/perf/util/cs-etm.c
> @@ -1134,10 +1134,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
>
> cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
>
> - if (etm->synth_opts.last_branch) {
> - cs_etm__copy_last_branch_rb(etmq, tidq);
> + if (etm->synth_opts.last_branch)
> sample.branch_stack = tidq->last_branch;
> - }
>
> if (etm->synth_opts.inject) {
> ret = cs_etm__inject_event(event, &sample,
> @@ -1407,6 +1405,10 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
> */
> u64 instrs_over = instrs_executed;
>
> + /* Prepare last branches for instruction sample */
> + if (etm->synth_opts.last_branch)
> + cs_etm__copy_last_branch_rb(etmq, tidq);
> +
> /*
> * 'head' is the instructions number of the head in the new
> * packet, it combines with the tail of previous packet to
> @@ -1526,6 +1528,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
>
> if (etmq->etm->synth_opts.last_branch &&
> tidq->prev_packet->sample_type == CS_ETM_RANGE) {
> + u64 addr;
> +
> + /* Prepare last branches for instruction sample */
> + cs_etm__copy_last_branch_rb(etmq, tidq);
> +
> /*
> * Generate a last branch event for the branches left in the
> * circular buffer at the end of the trace.
> @@ -1533,7 +1540,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
> * Use the address of the end of the last reported execution
> * range
> */
> - u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
> + addr = cs_etm__last_executed_instr(tidq->prev_packet);
>
> err = cs_etm__synth_instruction_sample(
> etmq, tidq, addr,
> @@ -1587,11 +1594,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
> */
> if (etmq->etm->synth_opts.last_branch &&
> tidq->prev_packet->sample_type == CS_ETM_RANGE) {
> + u64 addr;
> +
> + /* Prepare last branches for instruction sample */
> + cs_etm__copy_last_branch_rb(etmq, tidq);
> +
> /*
> * Use the address of the end of the last reported execution
> * range.
> */
> - u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
> + addr = cs_etm__last_executed_instr(tidq->prev_packet);
>
> err = cs_etm__synth_instruction_sample(
> etmq, tidq, addr,
> --
> 2.17.1
>


--
Mike Leach
Principal Engineer, ARM Ltd.
Manchester Design Centre. UK