perf c2c: Support data block and addr block

'perf c2c' is also a memory profiling tool. Apply the two new data
source fields to 'perf c2c' as well.

Extend 'perf c2c' to display the number of loads which blocked by data or
address conflict.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index d247f98..e3b9d63 100644 (file)
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2134,6 +2134,8 @@ static void print_c2c__display_stats(FILE *out)
        fprintf(out, "  Load MESI State Exclusive         : %10d\n", stats->ld_excl);
        fprintf(out, "  Load MESI State Shared            : %10d\n", stats->ld_shared);
        fprintf(out, "  Load LLC Misses                   : %10d\n", llc_misses);
+       fprintf(out, "  Load access blocked by data       : %10d\n", stats->blk_data);
+       fprintf(out, "  Load access blocked by address    : %10d\n", stats->blk_addr);
        fprintf(out, "  LLC Misses to Local DRAM          : %10.1f%%\n", ((double)stats->lcl_dram/(double)llc_misses) * 100.);
        fprintf(out, "  LLC Misses to Remote DRAM         : %10.1f%%\n", ((double)stats->rmt_dram/(double)llc_misses) * 100.);
        fprintf(out, "  LLC Misses to Remote cache (HIT)  : %10.1f%%\n", ((double)stats->rmt_hit /(double)llc_misses) * 100.);
@@ -2162,6 +2164,7 @@ static void print_shared_cacheline_info(FILE *out)
        fprintf(out, "  L2D hits on shared lines          : %10d\n", stats->ld_l2hit);
        fprintf(out, "  LLC hits on shared lines          : %10d\n", stats->ld_llchit + stats->lcl_hitm);
        fprintf(out, "  Locked Access on shared lines     : %10d\n", stats->locks);
+       fprintf(out, "  Blocked Access on shared lines    : %10d\n", stats->blk_data + stats->blk_addr);
        fprintf(out, "  Store HITs on shared lines        : %10d\n", stats->store);
        fprintf(out, "  Store L1D hits on shared lines    : %10d\n", stats->st_l1hit);
        fprintf(out, "  Total Merged records              : %10d\n", hitm_cnt + stats->store);

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 890f638..f93a852 100644 (file)
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -385,6 +385,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
        u64 lvl    = data_src->mem_lvl;
        u64 snoop  = data_src->mem_snoop;
        u64 lock   = data_src->mem_lock;
+       u64 blk    = data_src->mem_blk;
        /*
         * Skylake might report unknown remote level via this
         * bit, consider it when evaluating remote HITMs.
@@ -404,6 +405,9 @@ do {                                \
 
        if (lock & P(LOCK, LOCKED)) stats->locks++;
 
+       if (blk & P(BLK, DATA)) stats->blk_data++;
+       if (blk & P(BLK, ADDR)) stats->blk_addr++;
+
        if (op & P(OP, LOAD)) {
                /* load */
                stats->load++;
@@ -515,6 +519,8 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
        stats->rmt_hit          += add->rmt_hit;
        stats->lcl_dram         += add->lcl_dram;
        stats->rmt_dram         += add->rmt_dram;
+       stats->blk_data         += add->blk_data;
+       stats->blk_addr         += add->blk_addr;
        stats->nomap            += add->nomap;
        stats->noparse          += add->noparse;
 }

diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 5ddf447..755cef7 100644 (file)
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -79,6 +79,8 @@ struct c2c_stats {
        u32     rmt_hit;             /* count of loads with remote hit clean; */
        u32     lcl_dram;            /* count of loads miss to local DRAM */
        u32     rmt_dram;            /* count of loads miss to remote DRAM */
+       u32     blk_data;            /* count of loads blocked by data */
+       u32     blk_addr;            /* count of loads blocked by address conflict */
        u32     nomap;               /* count of load/stores with no phys adrs */
        u32     noparse;             /* count of unparsable data sources */
 };