perf vendor events amd: Add recommended events

Add support for events listed in Section 2.1.15.2 "Performance
Measurement" of "PPR for AMD Family 17h Model 31h B0 - 55803
Rev 0.54 - Sep 12, 2019".

perf now supports these new events (-e):

  all_dc_accesses
  all_tlbs_flushed
  l1_dtlb_misses
  l2_cache_accesses_from_dc_misses
  l2_cache_accesses_from_ic_misses
  l2_cache_hits_from_dc_misses
  l2_cache_hits_from_ic_misses
  l2_cache_misses_from_dc_misses
  l2_cache_misses_from_ic_miss
  l2_dtlb_misses
  l2_itlb_misses
  sse_avx_stalls
  uops_dispatched
  uops_retired
  l3_accesses
  l3_misses

and these metrics (-M):

  branch_misprediction_ratio
  all_l2_cache_accesses
  all_l2_cache_hits
  all_l2_cache_misses
  ic_fetch_miss_ratio
  l2_cache_accesses_from_l2_hwpf
  l2_cache_hits_from_l2_hwpf
  l2_cache_misses_from_l2_hwpf
  l3_read_miss_latency
  l1_itlb_misses
  all_remote_links_outbound
  nps1_die_to_dram

The nps1_die_to_dram event may need perf stat's --metric-no-group
switch if the number of available data fabric counters is less
than the number it uses (8).

Committer testing:

On a AMD Ryzen 3900x system:

Before:

  # perf list all_dc_accesses   all_tlbs_flushed   l1_dtlb_misses   l2_cache_accesses_from_dc_misses   l2_cache_accesses_from_ic_misses   l2_cache_hits_from_dc_misses   l2_cache_hits_from_ic_misses   l2_cache_misses_from_dc_misses   l2_cache_misses_from_ic_miss   l2_dtlb_misses   l2_itlb_misses   sse_avx_stalls   uops_dispatched   uops_retired   l3_accesses   l3_misses | grep -v "^Metric Groups:$" | grep -v "^$"
  #

After:

  # perf list all_dc_accesses   all_tlbs_flushed   l1_dtlb_misses   l2_cache_accesses_from_dc_misses   l2_cache_accesses_from_ic_misses   l2_cache_hits_from_dc_misses   l2_cache_hits_from_ic_misses   l2_cache_misses_from_dc_misses   l2_cache_misses_from_ic_miss   l2_dtlb_misses   l2_itlb_misses   sse_avx_stalls   uops_dispatched   uops_retired   l3_accesses   l3_misses | grep -v "^Metric Groups:$" | grep -v "^$" | grep -v "^recommended:$"
  all_dc_accesses
       [All L1 Data Cache Accesses]
  all_tlbs_flushed
       [All TLBs Flushed]
  l1_dtlb_misses
       [L1 DTLB Misses]
  l2_cache_accesses_from_dc_misses
       [L2 Cache Accesses from L1 Data Cache Misses (including prefetch)]
  l2_cache_accesses_from_ic_misses
       [L2 Cache Accesses from L1 Instruction Cache Misses (including
        prefetch)]
  l2_cache_hits_from_dc_misses
       [L2 Cache Hits from L1 Data Cache Misses]
  l2_cache_hits_from_ic_misses
       [L2 Cache Hits from L1 Instruction Cache Misses]
  l2_cache_misses_from_dc_misses
       [L2 Cache Misses from L1 Data Cache Misses]
  l2_cache_misses_from_ic_miss
       [L2 Cache Misses from L1 Instruction Cache Misses]
  l2_dtlb_misses
       [L2 DTLB Misses & Data page walks]
  l2_itlb_misses
       [L2 ITLB Misses & Instruction page walks]
  sse_avx_stalls
       [Mixed SSE/AVX Stalls]
  uops_dispatched
       [Micro-ops Dispatched]
  uops_retired
       [Micro-ops Retired]
  l3_accesses
       [L3 Accesses. Unit: amd_l3]
  l3_misses
       [L3 Misses (includes Chg2X). Unit: amd_l3]
  #

  # perf stat -a -e all_dc_accesses,all_tlbs_flushed,l1_dtlb_misses,l2_cache_accesses_from_dc_misses,l2_cache_accesses_from_ic_misses,l2_cache_hits_from_dc_misses,l2_cache_hits_from_ic_misses,l2_cache_misses_from_dc_misses,l2_cache_misses_from_ic_miss,l2_dtlb_misses,l2_itlb_misses,sse_avx_stalls,uops_dispatched,uops_retired,l3_accesses,l3_misses sleep 2

   Performance counter stats for 'system wide':

       433,439,949      all_dc_accesses                                               (35.66%)
               443      all_tlbs_flushed                                              (35.66%)
         2,985,885      l1_dtlb_misses                                                (35.66%)
        18,318,019      l2_cache_accesses_from_dc_misses                                     (35.68%)
        50,114,810      l2_cache_accesses_from_ic_misses                                     (35.72%)
        12,423,978      l2_cache_hits_from_dc_misses                                     (35.74%)
        40,703,103      l2_cache_hits_from_ic_misses                                     (35.74%)
         6,698,673      l2_cache_misses_from_dc_misses                                     (35.74%)
        12,090,892      l2_cache_misses_from_ic_miss                                     (35.74%)
           614,267      l2_dtlb_misses                                                (35.74%)
           216,036      l2_itlb_misses                                                (35.74%)
            11,977      sse_avx_stalls                                                (35.74%)
       999,276,223      uops_dispatched                                               (35.73%)
     1,075,311,620      uops_retired                                                  (35.69%)
         1,420,763      l3_accesses
           540,164      l3_misses

       2.002344121 seconds time elapsed

  # perf stat -a -e all_dc_accesses,all_tlbs_flushed,l1_dtlb_misses,l2_cache_accesses_from_dc_misses,l2_cache_accesses_from_ic_misses sleep 2

   Performance counter stats for 'system wide':

       175,943,104      all_dc_accesses
               310      all_tlbs_flushed
         2,280,359      l1_dtlb_misses
        11,700,151      l2_cache_accesses_from_dc_misses
        25,414,963      l2_cache_accesses_from_ic_misses

       2.001957818 seconds time elapsed

  #

Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Acked-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Jon Grimm <jon.grimm@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin Jambor <mjambor@suse.cz>
Cc: Martin Liška <mliska@suse.cz>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vijay Thakkar <vijaythakkar@me.com>
Cc: William Cohen <wcohen@redhat.com>
Cc: Yunfeng Ye <yeyunfeng@huawei.com>
Link: http://lore.kernel.org/lkml/20200901220944.277505-3-kim.phillips@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 1 insertions, 0 deletions

diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index fc9c158bfa13..e37d17830c5c 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -240,6 +240,7 @@ static struct map {
 	{ "hisi_sccl,hha", "hisi_sccl,hha" },
 	{ "hisi_sccl,l3c", "hisi_sccl,l3c" },
 	{ "L3PMC", "amd_l3" },
+	{ "DFPMC", "amd_df" },
 	{}
 };