[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f3aa49ff-958a-df73-f0cb-e48f73f70e8a@linux.intel.com>
Date: Wed, 20 Apr 2022 15:02:42 -0400
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Ali Saidi <alisaidi@...zon.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, german.gomez@....com,
leo.yan@...aro.org, acme@...nel.org
Cc: benh@...nel.crashing.org, Nick.Forrington@....com,
alexander.shishkin@...ux.intel.com, andrew.kilroy@....com,
james.clark@....com, john.garry@...wei.com, jolsa@...nel.org,
kjain@...ux.ibm.com, lihuafei1@...wei.com, mark.rutland@....com,
mathieu.poirier@...aro.org, mingo@...hat.com, namhyung@...nel.org,
peterz@...radead.org, will@...nel.org
Subject: Re: [PATCH v5 5/5] perf mem: Support mem_lvl_num in c2c command
On 4/8/2022 3:53 PM, Ali Saidi wrote:
> In addition to summarizing data encoded in mem_lvl also support data
> encoded in mem_lvl_num.
>
> Since other architectures don't seem to populate the mem_lvl_num field
> here there shouldn't be a change in functionality.
>
> Signed-off-by: Ali Saidi <alisaidi@...zon.com>
> ---
> tools/perf/util/mem-events.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
> index ed0ab838bcc5..e5e405185498 100644
> --- a/tools/perf/util/mem-events.c
> +++ b/tools/perf/util/mem-events.c
> @@ -485,6 +485,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
> u64 daddr = mi->daddr.addr;
> u64 op = data_src->mem_op;
> u64 lvl = data_src->mem_lvl;
> + u64 lnum = data_src->mem_lvl_num;
> u64 snoop = data_src->mem_snoop;
> u64 lock = data_src->mem_lock;
> u64 blk = data_src->mem_blk;
> @@ -527,16 +528,18 @@ do { \
> if (lvl & P(LVL, UNC)) stats->ld_uncache++;
> if (lvl & P(LVL, IO)) stats->ld_io++;
> if (lvl & P(LVL, LFB)) stats->ld_fbhit++;
> - if (lvl & P(LVL, L1 )) stats->ld_l1hit++;
> - if (lvl & P(LVL, L2 )) stats->ld_l2hit++;
> - if (lvl & P(LVL, L3 )) {
> + if (lvl & P(LVL, L1) || lnum == P(LVLNUM, L1))
> + stats->ld_l1hit++;
> + if (lvl & P(LVL, L2) || lnum == P(LVLNUM, L2))
> + stats->ld_l2hit++;
> + if (lvl & P(LVL, L3) || lnum == P(LVLNUM, L3)) {
> if (snoop & P(SNOOP, HITM))
> HITM_INC(lcl_hitm);
> else
> stats->ld_llchit++;
> }
>
> - if (lvl & P(LVL, LOC_RAM)) {
> + if (lvl & P(LVL, LOC_RAM) || lnum == P(LVLNUM, RAM)) {
I think the PERF_MEM_LVLNUM_RAM only means it's a DRAM.
It doesn't contain the location information. To distinguish the local
and remote dram, X86 uses PERF_MEM_REMOTE_REMOTE.
Here the remote dram will be mistakenly calculated if you only check the
PERF_MEM_LVLNUM_RAM.
Actually, it looks like the mem_lvl_num fields supported in this patch
are also supported by the PERF_MEM_LVL*. Why don't you set both
PERF_MEM_LVLNUM_* and PERF_MEM_LVL* in your previous patch 4?
Then you can drop this patch.
Thanks,
Kan
> stats->lcl_dram++;
> if (snoop & P(SNOOP, HIT))
> stats->ld_shared++;
Powered by blists - more mailing lists