From bc9e7fe313d5e56d4d5f34bcc04d1165f94f86fb Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 28 Jul 2022 10:39:46 +0100 Subject: perf python: Fix build when PYTHON_CONFIG is user supplied The previous change to Python autodetection had a small mistake where the auto value was used to determine the Python binary, rather than the user supplied value. The Python binary is only used for one part of the build process, rather than the final linking, so it was producing correct builds in most scenarios, especially when the auto detected value matched what the user wanted, or the system only had a valid set of Pythons. Change it so that the Python binary path is derived from either the PYTHON_CONFIG value or PYTHON value, depending on what is specified by the user. This was the original intention. This error was spotted in a build failure an odd cross compilation environment after commit 4c41cb46a732fe82 ("perf python: Prefer python3") was merged. Fixes: 630af16eee495f58 ("perf tools: Use Python devtools for version autodetection rather than runtime") Signed-off-by: James Clark Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220728093946.1337642-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0661a1cf9855..2171f02daf59 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -265,7 +265,7 @@ endif # defined. get-executable-or-default fails with an error if the first argument is supplied but # doesn't exist. override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO)) -override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO))) +override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG))) grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) -- cgit v1.2.3 From dbcfe5ec3f9a5799d8b49ad2c81549bbfa8390e7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 21 Dec 2020 12:53:44 -0300 Subject: tools kvm headers arm64: Update KVM header from the kernel sources To pick the changes from: ae3b1da95413614f ("KVM: arm64: Fix compile error due to sign extension") That doesn't result in any changes in tooling (when built on x86), only addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Marc Zyngier Cc: Namhyung Kim Cc: Yang Yingliang Link: https://lore.kernel.org/all/YwOMCCc4E79FuvDe@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 3bb134355874..316917b98707 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -75,9 +75,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 -- cgit v1.2.3 From bf515f024e4c0ca46a1b08c4f31860c01781d8a5 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 22 Aug 2022 14:33:51 -0700 Subject: perf stat: Clear evsel->reset_group for each stat run If a weak group is broken then the reset_group flag remains set for the next run. Having reset_group set means the counter isn't created and ultimately a segfault. A simple reproduction of this is: # perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W which will be added as a test in the next patch. Fixes: 4804e0111662d7d8 ("perf stat: Use affinity for opening events") Reviewed-by: Andi Kleen Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Tested-by: Xing Zhengjun Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220822213352.75721-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7fb81a44672d..54cd29d07ca8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) } evlist__for_each_entry(evsel_list, counter) { + counter->reset_group = false; if (bpf_counter__load(counter, &target)) return -1; if (!evsel__is_bpf(counter)) -- cgit v1.2.3 From 0c361c6eaba7fe1a29391540dd8797e850e49f21 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 22 Aug 2022 14:33:52 -0700 Subject: perf test: Stat test for repeat with a weak group Breaking a weak group requires multiple passes of an evlist, with multiple runs this can introduce bugs ultimately leading to segfaults. Add a test to cover this. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220822213352.75721-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat.sh | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 9313ef2739e0..26a51b48aee4 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,24 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_repeat_weak_groups() { + echo "stat repeat weak groups test" + if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ + true 2>&1 | grep -q 'seconds time elapsed' + then + echo "stat repeat weak groups test [Skipped event parsing failed]" + return + fi + if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \ + true > /dev/null 2>&1 + then + echo "stat repeat weak groups test [Failed]" + err=1 + return + fi + echo "stat repeat weak groups test [Success]" +} + test_topdown_groups() { # Topdown events must be grouped with the slots event first. Test that # parse-events reorders this. @@ -75,6 +93,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups exit $err -- cgit v1.2.3 From e89eaa611c7568d1288a2ccca88355a9434f2d47 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 18 Aug 2022 03:01:27 -0700 Subject: perf record: Fix manpage formatting of description of support to hybrid systems The Intel hybrid description is written in a different style than the rest of the perf record man page. There were some new command line options added after it which resulted in very strange section ordering. Move the hybrid include last. Also the sub sections in the hybrid document don't fit the record manpage well (especially since it talks about all kinds of unrelated commands). I left this for now, but would be better to separate this properly in the different man pages. It would be better to use sub sections for the other sections, but these don't seem to be supported in AsciiDoc? Some of the examples are still misrendered in the manpage with an indented troff command, but I don't know how to fix that. In any case it's now better than before. Signed-off-by: Andi Kleen Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220818100127.249401-1-ak@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/intel-hybrid.txt | 10 ---------- tools/perf/Documentation/perf-record.txt | 4 ++-- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt index c9302096dc46..e7a776ad25d7 100644 --- a/tools/perf/Documentation/intel-hybrid.txt +++ b/tools/perf/Documentation/intel-hybrid.txt @@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus. -Quickstart - -List hybrid event ------------------ - As before, use perf-list to list the symbolic event. perf list @@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can be supported. Enable hybrid event with a specific pmu ---------------------------------------- To enable a core only event or atom only event, following syntax is supported: @@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus. perf stat -e cpu_core/cycles/ Create two events for one hardware event automatically ------------------------------------------------------- When creating one event and the event is available on both atom and core, two events are created automatically. One is for atom, the other is for @@ -132,7 +125,6 @@ For perf-stat result, it displays two events: The first 'cycles' is core event, the second 'cycles' is atom event. Thread mode example: --------------------- perf-stat reports the scaled counts for hybrid event and with a percentage displayed. The percentage is the event's running time/enabling time. @@ -176,14 +168,12 @@ perf_event_attr: 604,097,080 cpu_atom/cycles/ (99.57%) perf-record: ------------- If there is no '-e' specified in perf record, on hybrid platform, it creates two default 'cycles' and adds them to event list. One is for core, the other is for atom. perf-stat: ----------- If there is no '-e' specified in perf stat, on hybrid platform, besides of software events, following events are created and diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 099817ef5150..6ec6d0ba0a72 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -757,8 +757,6 @@ events in data directory files. Option specified with no or empty value defaults to CPU layout. Masks defined or provided by the option value are filtered through the mask provided by -C option. -include::intel-hybrid.txt[] - --debuginfod[=URLs]:: Specify debuginfod URL to be used when cacheing perf.data binaries, it follows the same syntax as the DEBUGINFOD_URLS variable, like: @@ -778,6 +776,8 @@ include::intel-hybrid.txt[] only, as of now. So the applications built without the frame pointer might see bogus addresses. +include::intel-hybrid.txt[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1] -- cgit v1.2.3 From d72e5cf3cf69d4c68d3b54aea232451b0a8b69d3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 24 Aug 2022 07:57:33 -0700 Subject: perf sched: Fix memory leaks in __cmd_record detected with -fsanitize=address An array of strings is passed to cmd_record but not freed. As cmd_record modifies the array, add another array as a copy that can be mutated allowing the original array contents to all be freed. Detected with -fsanitize=address. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220824145733.409005-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 2f6cd1b8b662..a5cf243c337f 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void) static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; - const char **rec_argv; + char **rec_argv; + const char **rec_argv_copy; const char * const record_args[] = { "record", "-a", @@ -3384,6 +3385,7 @@ static int __cmd_record(int argc, const char **argv) ARRAY_SIZE(schedstat_args) : 0; struct tep_event *waking_event; + int ret; /* * +2 for either "-e", "sched:sched_wakeup" or @@ -3391,14 +3393,18 @@ static int __cmd_record(int argc, const char **argv) */ rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); - if (rec_argv == NULL) return -ENOMEM; + rec_argv_copy = calloc(rec_argc + 1, sizeof(char *)); + if (rec_argv_copy == NULL) { + free(rec_argv); + return -ENOMEM; + } for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = strdup(record_args[i]); - rec_argv[i++] = "-e"; + rec_argv[i++] = strdup("-e"); waking_event = trace_event__tp_format("sched", "sched_waking"); if (!IS_ERR(waking_event)) rec_argv[i++] = strdup("sched:sched_waking"); @@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv) rec_argv[i++] = strdup(schedstat_args[j]); for (j = 1; j < (unsigned int)argc; j++, i++) - rec_argv[i] = argv[j]; + rec_argv[i] = strdup(argv[j]); BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv); + memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc); + ret = cmd_record(rec_argc, rec_argv_copy); + + for (i = 0; i < rec_argc; i++) + free(rec_argv[i]); + free(rec_argv); + free(rec_argv_copy); + + return ret; } int cmd_sched(int argc, const char **argv) -- cgit v1.2.3 From 3126204ce3d9ab083cbdc2d61ab93746232eb89b Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 16 Aug 2022 05:56:12 -0700 Subject: perf docs: Update the documentation for the save_type filter Update the documentation to reflect the kernel changes. Signed-off-by: Kan Liang Cc: Andi Kleen Cc: Ian Rogers Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220816125612.2042397-2-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 6ec6d0ba0a72..0228efc96686 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -397,6 +397,9 @@ following filters are defined: - abort_tx: only when the target is a hardware transaction abort - cond: conditional branches - save_type: save branch type during sampling in case binary is not available later + For the platforms with Intel Arch LBR support (12th-Gen+ client or + 4th-Gen Xeon+ server), the save branch type is unconditionally enabled + when the taken branch stack sampling is enabled. + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. -- cgit v1.2.3 From 48648548ef764dcb1f6ffc9c9f9057f7c610caa4 Mon Sep 17 00:00:00 2001 From: Zhengjun Xing Date: Thu, 25 Aug 2022 09:54:58 +0800 Subject: perf stat: Capitalize topdown metrics' names Capitalize topdown metrics' names to follow the intel SDM. Before: # ./perf stat -a sleep 1 Performance counter stats for 'system wide': 228,094.05 msec cpu-clock # 225.026 CPUs utilized 842 context-switches # 3.691 /sec 224 cpu-migrations # 0.982 /sec 70 page-faults # 0.307 /sec 23,164,105 cycles # 0.000 GHz 29,403,446 instructions # 1.27 insn per cycle 5,268,185 branches # 23.097 K/sec 33,239 branch-misses # 0.63% of all branches 136,248,990 slots # 597.337 K/sec 32,976,450 topdown-retiring # 24.2% retiring 4,651,918 topdown-bad-spec # 3.4% bad speculation 26,148,695 topdown-fe-bound # 19.2% frontend bound 72,515,776 topdown-be-bound # 53.2% backend bound 6,008,540 topdown-heavy-ops # 4.4% heavy operations # 19.8% light operations 3,934,049 topdown-br-mispredict # 2.9% branch mispredict # 0.5% machine clears 16,655,439 topdown-fetch-lat # 12.2% fetch latency # 7.0% fetch bandwidth 41,635,972 topdown-mem-bound # 30.5% memory bound # 22.7% Core bound 1.013634593 seconds time elapsed After: # ./perf stat -a sleep 1 Performance counter stats for 'system wide': 228,081.94 msec cpu-clock # 225.003 CPUs utilized 824 context-switches # 3.613 /sec 224 cpu-migrations # 0.982 /sec 67 page-faults # 0.294 /sec 22,647,423 cycles # 0.000 GHz 28,870,551 instructions # 1.27 insn per cycle 5,167,099 branches # 22.655 K/sec 32,383 branch-misses # 0.63% of all branches 133,411,074 slots # 584.926 K/sec 32,352,607 topdown-retiring # 24.3% Retiring 4,456,977 topdown-bad-spec # 3.3% Bad Speculation 25,626,487 topdown-fe-bound # 19.2% Frontend Bound 70,955,316 topdown-be-bound # 53.2% Backend Bound 5,834,844 topdown-heavy-ops # 4.4% Heavy Operations # 19.9% Light Operations 3,738,781 topdown-br-mispredict # 2.8% Branch Mispredict # 0.5% Machine Clears 16,286,803 topdown-fetch-lat # 12.2% Fetch Latency # 7.0% Fetch Bandwidth 40,802,069 topdown-mem-bound # 30.6% Memory Bound # 22.6% Core Bound 1.013683125 seconds time elapsed Reviewed-by: Kan Liang Signed-off-by: Xing Zhengjun Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220825015458.3252239-1-zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 979c8cb918f7..788ce5e46470 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (retiring > 0.7) color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "retiring", + print_metric(config, ctxp, color, "%8.1f%%", "Retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && full_td(cpu_map_idx, st, &rsd)) { @@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (fe_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", + print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && full_td(cpu_map_idx, st, &rsd)) { @@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (be_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "backend bound", + print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound", be_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && full_td(cpu_map_idx, st, &rsd)) { @@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, &rsd); if (bad_spec > 0.1) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", + print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (retiring > 0.7 && heavy_ops > 0.1) color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "heavy operations", + print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations", heavy_ops * 100.); if (retiring > 0.7 && light_ops > 0.6) color = PERF_COLOR_GREEN; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "light operations", + print_metric(config, ctxp, color, "%8.1f%%", "Light Operations", light_ops * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (bad_spec > 0.1 && br_mis > 0.05) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict", + print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict", br_mis * 100.); if (bad_spec > 0.1 && m_clears > 0.05) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "machine clears", + print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears", m_clears * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (fe_bound > 0.2 && fetch_lat > 0.15) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "fetch latency", + print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency", fetch_lat * 100.); if (fe_bound > 0.2 && fetch_bw > 0.1) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth", + print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth", fetch_bw * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { @@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (be_bound > 0.2 && mem_bound > 0.2) color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "memory bound", + print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound", mem_bound * 100.); if (be_bound > 0.2 && core_bound > 0.1) color = PERF_COLOR_RED; else color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Core bound", + print_metric(config, ctxp, color, "%8.1f%%", "Core Bound", core_bound * 100.); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, -- cgit v1.2.3