diff options
| author | Adrian Hunter <adrian.hunter@intel.com> | 2021-02-05 18:53:48 +0100 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2021-02-18 20:03:37 +0100 |
| commit | 20aa39708a5999b7921b27482a756766272286ac (patch) | |
| tree | 66de40f6014defdcb5cfc0153ba30bf2164ff433 /tools/perf/util/intel-pt.c | |
| parent | perf intel-pt: Fix missing CYC processing in PSB (diff) | |
| download | linux-20aa39708a5999b7921b27482a756766272286ac.tar.xz linux-20aa39708a5999b7921b27482a756766272286ac.zip | |
perf intel-pt: Fix premature IPC
The code assumed a change in cycle count means accurate IPC. That is not
correct, for example when sampling both branches and instructions, or at
a FUP packet (which is not CYC-eligible) address. Fix by using an explicit
flag to indicate when IPC can be sampled.
Fixes: 5b1dc0fd1da06 ("perf intel-pt: Add support for samples to contain IPC ratio")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: linux-kernel@vger.kernel.org
Link: https://lore.kernel.org/r/20210205175350.23817-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/intel-pt.c')
| -rw-r--r-- | tools/perf/util/intel-pt.c | 16 |
1 files changed, 6 insertions, 10 deletions
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index c9477d021687..c63a9080c1b1 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1381,7 +1381,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt; + 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; @@ -1431,7 +1432,8 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) else sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_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; @@ -1983,14 +1985,8 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - if (ptq->state->tot_cyc_cnt > ptq->ipc_cyc_cnt) { - /* - * Cycle count and instruction count only go together to create - * a valid IPC ratio when the cycle count changes. - */ - ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; - ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt; - } + 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 |