From 6145b2d098b96e1f7801f2f458d56b4159e471c1 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 19 Oct 2020 08:36:13 +0800 Subject: [PATCH 1/8] perf mem2node: Improve warning if detected no memory nodes ANBZ: #877 commit 0ee281e1e4e12f8c09b99f80a2482a55cd7d6bca upstream. Some archs (e.g. x86 and Arm64) don't enable the configuration CONFIG_MEMORY_HOTPLUG by default, if this configuration is not enabled when build the kernel image, the SysFS for memory nodes will be missed. This results in perf tool has no chance to catpure the memory nodes information, when perf tool reports the result and detects no memory nodes, it outputs "assertion failed at util/mem2node.c:99". The output log doesn't give out reason for the failure and users have no clue for how to fix it. This patch changes to use explicit way for warning: it tells user that detected no memory nodes and suggests to enable CONFIG_MEMORY_HOTPLUG for kernel building. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201019003613.8399-1-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/util/mem2node.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index c84f5841c7ab..03a7d7b27737 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env) /* Cut unused entries, due to merging. */ tmp_entries = realloc(entries, sizeof(*entries) * j); - if (tmp_entries || WARN_ON_ONCE(j == 0)) + if (tmp_entries || + WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n")) entries = tmp_entries; for (i = 0; i < j; i++) { -- Gitee From 4eeb994212d89ce9ec47bd1f846f80d78cd2cb07 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:45 +0800 Subject: [PATCH 2/8] perf mem: Search event name with more flexible path ANBZ: #877 commit f9f16dfbe76e63ba9aec68055c08242b09be297e upstream. The perf tool searches a memory event name under the folder '/sys/devices/cpu/events/', this leads to the limitation for the selection of a memory profiling event which must be under this folder. Thus it's impossible to use any other event as memory event which is not under this specific folder, e.g. Arm SPE hardware event is not located in '/sys/devices/cpu/events/' so it cannot be enabled for memory profiling. This patch changes to search folder from '/sys/devices/cpu/events/' to '/sys/devices', so it give flexibility to find events which can be used for memory profiling. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/util/mem-events.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 211565e74d7b..6a08a36f757f 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -18,8 +18,8 @@ unsigned int perf_mem_events__loads_ldlat = 30; #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { - E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"), - E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"), + E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"), + E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"), }; #undef E @@ -93,7 +93,7 @@ int perf_mem_events__init(void) struct perf_mem_event *e = &perf_mem_events[j]; struct stat st; - scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s", + scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, e->sysfs_name); if (!stat(path, &st)) -- Gitee From 0b8c1486a0f81958cf59080b21c8105e91f0c062 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:46 +0800 Subject: [PATCH 3/8] perf mem: Introduce weak function perf_mem_events__ptr() ANBZ: #877 commit eaf6aaeec5fa301c0eb8ae92962909b15d075e5f upstream. Different architectures might use different event or different event parameters for memory profiling, this patch introduces a weak perf_mem_events__ptr() function which allows to return back a architecture specific memory event. Since the variable 'perf_mem_events' can be only accessed by the perf_mem_events__ptr() function, mark the variable as 'static', this allows the architectures to define its own memory event array. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-3-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/builtin-c2c.c | 18 ++++++++++++------ tools/perf/builtin-mem.c | 21 ++++++++++++++------- tools/perf/util/mem-events.c | 26 +++++++++++++++++++------- tools/perf/util/mem-events.h | 2 +- 4 files changed, 46 insertions(+), 21 deletions(-) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 5a3b0bf455f4..a693abdfa9ee 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -3048,6 +3048,7 @@ static int perf_c2c__record(int argc, const char **argv) int ret; bool all_user = false, all_kernel = false; bool event_set = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &event_set, "event", "event selector. Use 'perf c2c record -e list' to list available events", @@ -3075,11 +3076,15 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "record"; if (!event_set) { - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -3087,12 +3092,13 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "--sample-cpu"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", - perf_mem_events[j].name); + perf_mem_events__name(j)); free(rec_argv); return -1; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 3523279af6af..9a7df8d01296 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -64,6 +64,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) const char **rec_argv; int ret; bool all_user = false, all_kernel = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &mem, "event", "event selector. use 'perf mem record -e list' to list available events", @@ -86,13 +87,18 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "record"; - if (mem->operation & MEM_OPERATION_LOAD) - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + if (mem->operation & MEM_OPERATION_LOAD) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + } - if (mem->operation & MEM_OPERATION_STORE) - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + if (mem->operation & MEM_OPERATION_STORE) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -101,10 +107,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "--phys-data"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", perf_mem_events__name(j)); free(rec_argv); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 6a08a36f757f..594140543a03 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -17,7 +17,7 @@ unsigned int perf_mem_events__loads_ldlat = 30; #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } -struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"), E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"), }; @@ -28,19 +28,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; +struct perf_mem_event * __weak perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + char * __weak perf_mem_events__name(int i) { + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (!e) + return NULL; + if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { mem_loads_name__init = true; scnprintf(mem_loads_name, sizeof(mem_loads_name), - perf_mem_events[i].name, - perf_mem_events__loads_ldlat); + e->name, perf_mem_events__loads_ldlat); } return mem_loads_name; } - return (char *)perf_mem_events[i].name; + return (char *)e->name; } int perf_mem_events__parse(const char *str) @@ -61,7 +73,7 @@ int perf_mem_events__parse(const char *str) while (tok) { for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); if (strstr(e->tag, tok)) e->record = found = true; @@ -90,7 +102,7 @@ int perf_mem_events__init(void) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { char path[PATH_MAX]; - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); struct stat st; scnprintf(path, PATH_MAX, "%s/devices/%s", @@ -108,7 +120,7 @@ void perf_mem_events__list(void) int j; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); fprintf(stderr, "%-13s%-*s%s\n", e->tag, diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 13c198003a57..55265b4e4965 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -31,13 +31,13 @@ enum { PERF_MEM_EVENTS__MAX, }; -extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX]; extern unsigned int perf_mem_events__loads_ldlat; int perf_mem_events__parse(const char *str); int perf_mem_events__init(void); char *perf_mem_events__name(int i); +struct perf_mem_event *perf_mem_events__ptr(int i); void perf_mem_events__list(void); -- Gitee From 94bf1588ba516ca41a7f6e4b9f6c2360442329ae Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:47 +0800 Subject: [PATCH 4/8] perf mem: Support new memory event PERF_MEM_EVENTS__LOAD_STORE ANBZ: #877 commit 4ba2452cd88f39da68a6dc05fcc95e8977fd6403 upstream. On the architectures with perf memory profiling, two types of hardware events have been supported: load and store; if want to profile memory for both load and store operations, the tool will use these two events at the same time, the usage is: # perf mem record -t load,store -- uname But this cannot be applied for AUX tracing event, the same PMU event can be used to only trace memory load, or only memory store, or trace for both memory load and store. This patch introduces a new event PERF_MEM_EVENTS__LOAD_STORE, which is used to support the event which can record both memory load and store operations. When user specifies memory operation type as 'load,store', or doesn't set type so use 'load,store' as default, if the arch supports the event PERF_MEM_EVENTS__LOAD_STORE, the tool will convert the required operations to this single event; otherwise, if the arch doesn't support PERF_MEM_EVENTS__LOAD_STORE, the tool rolls back to enable both events PERF_MEM_EVENTS__LOAD and PERF_MEM_EVENTS__STORE, which keeps the same behaviour with before. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-4-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/builtin-mem.c | 24 ++++++++++++++++++------ tools/perf/util/mem-events.c | 13 ++++++++++++- tools/perf/util/mem-events.h | 1 + 3 files changed, 31 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 9a7df8d01296..21ebe0f47e64 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -87,14 +87,26 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "record"; - if (mem->operation & MEM_OPERATION_LOAD) { - e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); - e->record = true; - } + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE); - if (mem->operation & MEM_OPERATION_STORE) { - e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + /* + * The load and store operations are required, use the event + * PERF_MEM_EVENTS__LOAD_STORE if it is supported. + */ + if (e->tag && + (mem->operation & MEM_OPERATION_LOAD) && + (mem->operation & MEM_OPERATION_STORE)) { e->record = true; + } else { + if (mem->operation & MEM_OPERATION_LOAD) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + } + + if (mem->operation & MEM_OPERATION_STORE) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } } e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 594140543a03..b174591479bf 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -20,6 +20,7 @@ unsigned int perf_mem_events__loads_ldlat = 30; static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"), E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"), + E(NULL, NULL, NULL), }; #undef E @@ -75,6 +76,9 @@ int perf_mem_events__parse(const char *str) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { struct perf_mem_event *e = perf_mem_events__ptr(j); + if (!e->tag) + continue; + if (strstr(e->tag, tok)) e->record = found = true; } @@ -105,6 +109,13 @@ int perf_mem_events__init(void) struct perf_mem_event *e = perf_mem_events__ptr(j); struct stat st; + /* + * If the event entry isn't valid, skip initialization + * and "e->supported" will keep false. + */ + if (!e->tag) + continue; + scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, e->sysfs_name); @@ -123,7 +134,7 @@ void perf_mem_events__list(void) struct perf_mem_event *e = perf_mem_events__ptr(j); fprintf(stderr, "%-13s%-*s%s\n", - e->tag, + e->tag ?: "", verbose > 0 ? 25 : 0, verbose > 0 ? perf_mem_events__name(j) : "", e->supported ? ": available" : ""); diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 55265b4e4965..4fb9870971e0 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -28,6 +28,7 @@ struct mem_info { enum { PERF_MEM_EVENTS__LOAD, PERF_MEM_EVENTS__STORE, + PERF_MEM_EVENTS__LOAD_STORE, PERF_MEM_EVENTS__MAX, }; -- Gitee From db8b00917f2b3b8bcd95b13b22b936e536c71728 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:49 +0800 Subject: [PATCH 5/8] perf mem: Only initialize memory event for recording ANBZ: #877 commit 436cce00710a3f234ab6b735b5980256e773d388 upstream. It's needless to initialize memory events for reporting, this patch moves memory event initialization for only recording. Furthermore, the change allows to parse perf data on cross platforms, e.g. perf tool can report result properly even the machine doesn't support the memory events. Signed-off-by: Leo Yan Acked-by: Ian Rogers Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-6-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/builtin-mem.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 21ebe0f47e64..72ce4b8fbb0f 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -77,6 +77,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) OPT_END() }; + if (perf_mem_events__init()) { + pr_err("failed: memory events not supported\n"); + return -1; + } + argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); @@ -441,11 +446,6 @@ int cmd_mem(int argc, const char **argv) NULL }; - if (perf_mem_events__init()) { - pr_err("failed: memory events not supported\n"); - return -1; - } - argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_KEEP_UNKNOWN); -- Gitee From 84ff25a37bf93781626bc3533f7ca1bd0c0e58bd Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:50 +0800 Subject: [PATCH 6/8] perf auxtrace: Add itrace option '-M' for memory events ANBZ: #877 commit 014a771c7867fda5b40a95e1c7bc1aa5ac704c91 upstream. This patch is to add itrace option '-M' to synthesize memory event. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-7-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/Documentation/itrace.txt | 1 + tools/perf/util/auxtrace.c | 4 ++++ tools/perf/util/auxtrace.h | 2 ++ 3 files changed, 7 insertions(+) diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index d3740c8f399b..079cdfabb352 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -11,6 +11,7 @@ d create a debug log f synthesize first level cache events m synthesize last level cache events + M synthesize memory events t synthesize TLB events a synthesize remote access events g synthesize a call chain (use with i or x) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index d20250c2e7c4..f6377a3cab16 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1329,6 +1329,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->flc = true; synth_opts->llc = true; synth_opts->tlb = true; + synth_opts->mem = true; synth_opts->remote_access = true; if (no_sample) { @@ -1550,6 +1551,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'a': synth_opts->remote_access = true; break; + case 'M': + synth_opts->mem = true; + break; case 'q': synth_opts->quick += 1; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index da8f3df70e4b..bbaa06a769fb 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -88,6 +88,7 @@ enum itrace_period_type { * @llc: whether to synthesize last level cache events * @tlb: whether to synthesize TLB events * @remote_access: whether to synthesize remote access events + * @mem: whether to synthesize memory events * @callchain_sz: maximum callchain size * @last_branch_sz: branch context size * @period: 'instructions' events period @@ -126,6 +127,7 @@ struct itrace_synth_opts { bool llc; bool tlb; bool remote_access; + bool mem; unsigned int callchain_sz; unsigned int last_branch_sz; unsigned long long period; -- Gitee From c62307870260913c90742db124a260dc57501afb Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:51 +0800 Subject: [PATCH 7/8] perf mem: Support AUX trace ANBZ: #877 commit 13e5df1e3f1ba1a90944362bc57690ea1369b3b7 upstream. The 'perf mem' tool doesn't support AUX trace data so it cannot receive the hardware tracing data. On arm64, although it doesn't support PMU events for memory load and store, ARM SPE is a good candidate for memory profiling, the hardware tracer can record memory accessing operations with affiliated information (e.g. physical address and virtual address for accessing, cache levels, TLB walking, latency, etc). To allow "perf mem" tool to support AUX trace, this patch adds the AUX callbacks for session structure; make itrace memory event as default for "perf mem", this tells the AUX trace decoder to synthesize memory samples. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-8-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/builtin-mem.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 72ce4b8fbb0f..fdfbff7592f4 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -7,6 +7,7 @@ #include "perf.h" #include +#include "util/auxtrace.h" #include "util/trace-event.h" #include "util/tool.h" #include "util/session.h" @@ -255,6 +256,12 @@ static int process_sample_event(struct perf_tool *tool, static int report_raw_events(struct perf_mem *mem) { + struct itrace_synth_opts itrace_synth_opts = { + .set = true, + .mem = true, /* Only enable memory event */ + .default_no_sample = true, + }; + struct perf_data data = { .path = input_name, .mode = PERF_DATA_MODE_READ, @@ -267,6 +274,8 @@ static int report_raw_events(struct perf_mem *mem) if (IS_ERR(session)) return PTR_ERR(session); + session->itrace_synth_opts = &itrace_synth_opts; + if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, mem->cpu_bitmap); @@ -410,8 +419,12 @@ int cmd_mem(int argc, const char **argv) .comm = perf_event__process_comm, .lost = perf_event__process_lost, .fork = perf_event__process_fork, + .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, .namespaces = perf_event__process_namespaces, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .auxtrace_error = perf_event__process_auxtrace_error, .ordered_events = true, }, .input_name = "perf.data", -- Gitee From 7bd083621928fd57a5928af850384130a5966031 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Fri, 6 Nov 2020 17:48:53 +0800 Subject: [PATCH 8/8] perf mem: Support ARM SPE events ANBZ: #877 commit 40714c58630aaaf1eb3acc431fe206a6b36a03d6 upstream. This patch adds ARM SPE events for perf memory profiling: 'spe-load': event for only recording memory load ops; 'spe-store': event for only recording memory store ops; 'spe-ldst': event for recording memory load and store ops. Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201106094853.21082-10-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Shuai Xue Reviewed-by: Baolin Wang --- tools/perf/arch/arm64/util/Build | 2 +- tools/perf/arch/arm64/util/mem-events.c | 37 +++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) create mode 100644 tools/perf/arch/arm64/util/mem-events.c diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index b53294d74b01..cf6d7e799f33 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -9,4 +9,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ ../../arm/util/cs-etm.o \ - arm-spe.o + arm-spe.o mem-events.o diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c new file mode 100644 index 000000000000..2a2497372671 --- /dev/null +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "map_symbol.h" +#include "mem-events.h" + +#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } + +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("spe-load", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=0,min_latency=%u/", "arm_spe_0"), + E("spe-store", "arm_spe_0/ts_enable=1,load_filter=0,store_filter=1/", "arm_spe_0"), + E("spe-ldst", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=1,min_latency=%u/", "arm_spe_0"), +}; + +static char mem_ev_name[100]; + +struct perf_mem_event *perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + +char *perf_mem_events__name(int i) +{ + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) + scnprintf(mem_ev_name, sizeof(mem_ev_name), + e->name, perf_mem_events__loads_ldlat); + else /* PERF_MEM_EVENTS__STORE */ + scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name); + + return mem_ev_name; +} -- Gitee