Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Leo Yan <leo.yan@linaro.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Like Xu <likexu@tencent.com>, Alyssa Ross <hi@alyssa.is>,
        Ian Rogers <irogers@google.com>,
        Kajol Jain <kjain@linux.ibm.com>,
        Adam Li <adamli@amperemail.onmicrosoft.com>,
        Li Huafei <lihuafei1@huawei.com>,
        German Gomez <german.gomez@arm.com>,
        James Clark <james.clark@arm.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Ali Saidi <alisaidi@amazon.com>, Joe Mario <jmario@redhat.com>,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     Leo Yan <leo.yan@linaro.org>
Subject: [PATCH v3 04/11] perf mem: Add statistics for peer snooping
Date:   Wed, 18 May 2022 13:57:22 +0800
Message-Id: <20220518055729.1869566-5-leo.yan@linaro.org>
In-Reply-To: <20220518055729.1869566-1-leo.yan@linaro.org>
References: <20220518055729.1869566-1-leo.yan@linaro.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Since the flag PERF_MEM_SNOOPX_PEER is added to support cache snooping
from peer cache line, it can come from a peer core, a peer cluster, or
a remote NUMA node.

This patch adds statistics for the flag PERF_MEM_SNOOPX_PEER.  Note, we
take PERF_MEM_SNOOPX_PEER as an affiliated info, it needs to cooperate
with cache level statistics.  Therefore, we account the load operations
for both the cache level's metrics (e.g. ld_l2hit, ld_llchit, etc.) and
the metric 'ld_peer' when flag PERF_MEM_SNOOPX_PEER is set.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Tested-by: Ali Saidi <alisaidi@amazon.com>
---
 tools/perf/util/mem-events.c | 22 +++++++++++++++++++---
 tools/perf/util/mem-events.h |  1 +
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 5dca1882c284..9de0eb3a1200 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -525,6 +525,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 	u64 op     = data_src->mem_op;
 	u64 lvl    = data_src->mem_lvl;
 	u64 snoop  = data_src->mem_snoop;
+	u64 snoopx = data_src->mem_snoopx;
 	u64 lock   = data_src->mem_lock;
 	u64 blk    = data_src->mem_blk;
 	/*
@@ -567,18 +568,28 @@ do {				\
 			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, L2)) {
+				stats->ld_l2hit++;
+
+				if (snoopx & P(SNOOPX, PEER))
+					stats->ld_peer++;
+			}
 			if (lvl & P(LVL, L3 )) {
 				if (snoop & P(SNOOP, HITM))
 					HITM_INC(lcl_hitm);
 				else
 					stats->ld_llchit++;
+
+				if (snoopx & P(SNOOPX, PEER))
+					stats->ld_peer++;
 			}
 
 			if (lvl & P(LVL, LOC_RAM)) {
 				stats->lcl_dram++;
 				if (snoop & P(SNOOP, HIT))
 					stats->ld_shared++;
+				else if (snoopx & P(SNOOPX, PEER))
+					stats->ld_peer++;
 				else
 					stats->ld_excl++;
 			}
@@ -597,10 +608,14 @@ do {				\
 		if ((lvl & P(LVL, REM_CCE1)) ||
 		    (lvl & P(LVL, REM_CCE2)) ||
 		     mrem) {
-			if (snoop & P(SNOOP, HIT))
+			if (snoop & P(SNOOP, HIT)) {
 				stats->rmt_hit++;
-			else if (snoop & P(SNOOP, HITM))
+			} else if (snoop & P(SNOOP, HITM)) {
 				HITM_INC(rmt_hitm);
+			} else if (snoopx & P(SNOOPX, PEER)) {
+				stats->rmt_hit++;
+				stats->ld_peer++;
+			}
 		}
 
 		if ((lvl & P(LVL, MISS)))
@@ -661,6 +676,7 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
 	stats->ld_l1hit		+= add->ld_l1hit;
 	stats->ld_l2hit		+= add->ld_l2hit;
 	stats->ld_llchit	+= add->ld_llchit;
+	stats->ld_peer		+= add->ld_peer;
 	stats->lcl_hitm		+= add->lcl_hitm;
 	stats->rmt_hitm		+= add->rmt_hitm;
 	stats->tot_hitm		+= add->tot_hitm;
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 8a8b568baeee..4879b841c841 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -75,6 +75,7 @@ struct c2c_stats {
 	u32	ld_l1hit;            /* count of loads that hit L1D */
 	u32	ld_l2hit;            /* count of loads that hit L2D */
 	u32	ld_llchit;           /* count of loads that hit LLC */
+	u32	ld_peer;             /* count of loads that hit peer core or cluster cache */
 	u32	lcl_hitm;            /* count of loads with local HITM  */
 	u32	rmt_hitm;            /* count of loads with remote HITM */
 	u32	tot_hitm;            /* count of loads with local and remote HITM */
-- 
2.25.1