forked from luck/tmp_suning_uos_patched
perf/urgent fixes:
perf stat:
- Keep the '/' event modifier separator in fallback, for example when
fallbacking from 'cpu/cpu-cycles/' to user level only, where it should
become 'cpu/cpu-cycles/u' and not 'cpu/cpu-cycles/:u' (Jiri Olsa)
- Fix PMU events parsing rule, improving error reporting for
invalid events (Jiri Olsa)
- Disable write_backward and other event attributes for !group
events in a group, fixing, for instance this group: '{cycles,msr/aperf/}:S'
that has leader sampling (:S) and where just the 'cycles',
the leader event, should have the write_backward attribute
set, in this case it all fails because the PMU where 'msr/aperf/'
lives doesn't accepts write_backward style sampling (Jiri Olsa)
- Only fall back group read for leader (Kan Liang)
- Fix core PMU alias list for X86 platform (Kan Liang)
- Print out hint for mixed PMU group error (Kan Liang)
- Fix duplicate PMU name for interval print (Kan Liang)
Core:
- Set main kernel end address properly when reading kernel and
module maps (Namhyung Kim)
perf mem:
- Fix incorrect entries and add missing man options (Sangwon Hong)
s/390:
- Remove s390 specific strcmp_cpuid_cmp function (Thomas Richter)
- Adapt 'perf test' case record+probe_libc_inet_pton.sh for s390
- Fix s390 undefined record__auxtrace_init() return value in
'perf record' (Thomas Richter)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----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=dEfn
-----END PGP SIGNATURE-----
Merge tag 'perf-urgent-for-mingo-4.17-20180425' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
perf stat:
- Keep the '/' event modifier separator in fallback, for example when
fallbacking from 'cpu/cpu-cycles/' to user level only, where it should
become 'cpu/cpu-cycles/u' and not 'cpu/cpu-cycles/:u' (Jiri Olsa)
- Fix PMU events parsing rule, improving error reporting for
invalid events (Jiri Olsa)
- Disable write_backward and other event attributes for !group
events in a group, fixing, for instance this group: '{cycles,msr/aperf/}:S'
that has leader sampling (:S) and where just the 'cycles',
the leader event, should have the write_backward attribute
set, in this case it all fails because the PMU where 'msr/aperf/'
lives doesn't accepts write_backward style sampling (Jiri Olsa)
- Only fall back group read for leader (Kan Liang)
- Fix core PMU alias list for x86 platform (Kan Liang)
- Print out hint for mixed PMU group error (Kan Liang)
- Fix duplicate PMU name for interval print (Kan Liang)
Core:
- Set main kernel end address properly when reading kernel and
module maps (Namhyung Kim)
perf mem:
- Fix incorrect entries and add missing man options (Sangwon Hong)
s/390:
- Remove s390 specific strcmp_cpuid_cmp function (Thomas Richter)
- Adapt 'perf test' case record+probe_libc_inet_pton.sh for s390
- Fix s390 undefined record__auxtrace_init() return value in
'perf record' (Thomas Richter)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
commit
d4652f614f
|
|
@ -28,29 +28,46 @@ OPTIONS
|
|||
<command>...::
|
||||
Any command you can specify in a shell.
|
||||
|
||||
-i::
|
||||
--input=<file>::
|
||||
Input file name.
|
||||
|
||||
-f::
|
||||
--force::
|
||||
Don't do ownership validation
|
||||
|
||||
-t::
|
||||
--type=::
|
||||
--type=<type>::
|
||||
Select the memory operation type: load or store (default: load,store)
|
||||
|
||||
-D::
|
||||
--dump-raw-samples=::
|
||||
--dump-raw-samples::
|
||||
Dump the raw decoded samples on the screen in a format that is easy to parse with
|
||||
one sample per line.
|
||||
|
||||
-x::
|
||||
--field-separator::
|
||||
--field-separator=<separator>::
|
||||
Specify the field separator used when dump raw samples (-D option). By default,
|
||||
The separator is the space character.
|
||||
|
||||
-C::
|
||||
--cpu-list::
|
||||
Restrict dump of raw samples to those provided via this option. Note that the same
|
||||
option can be passed in record mode. It will be interpreted the same way as perf
|
||||
record.
|
||||
--cpu=<cpu>::
|
||||
Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
|
||||
comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default
|
||||
is to monitor all CPUS.
|
||||
-U::
|
||||
--hide-unresolved::
|
||||
Only display entries resolved to a symbol.
|
||||
|
||||
-p::
|
||||
--phys-data::
|
||||
Record/Report sample physical addresses
|
||||
|
||||
RECORD OPTIONS
|
||||
--------------
|
||||
-e::
|
||||
--event <event>::
|
||||
Event selector. Use 'perf mem record -e list' to list available events.
|
||||
|
||||
-K::
|
||||
--all-kernel::
|
||||
|
|
@ -60,12 +77,12 @@ OPTIONS
|
|||
--all-user::
|
||||
Configure all used events to run in user space.
|
||||
|
||||
--ldload::
|
||||
Specify desired latency for loads event.
|
||||
-v::
|
||||
--verbose::
|
||||
Be more verbose (show counter open errors, etc)
|
||||
|
||||
-p::
|
||||
--phys-data::
|
||||
Record/Report sample physical addresses
|
||||
--ldlat <n>::
|
||||
Specify desired latency for loads event.
|
||||
|
||||
In addition, for report all perf report options are valid, and for record
|
||||
all perf record options.
|
||||
|
|
|
|||
|
|
@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
|
|||
struct perf_evsel *pos;
|
||||
int diagnose = 0;
|
||||
|
||||
*err = 0;
|
||||
if (evlist->nr_entries == 0)
|
||||
return NULL;
|
||||
|
||||
|
|
|
|||
|
|
@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
|
|||
zfree(&buf);
|
||||
return buf;
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare the cpuid string returned by get_cpuid() function
|
||||
* with the name generated by the jevents file read from
|
||||
* pmu-events/arch/s390/mapfile.csv.
|
||||
*
|
||||
* Parameter mapcpuid is the cpuid as stored in the
|
||||
* pmu-events/arch/s390/mapfile.csv. This is just the type number.
|
||||
* Parameter cpuid is the cpuid returned by function get_cpuid().
|
||||
*/
|
||||
int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
|
||||
{
|
||||
char *cp = strchr(cpuid, ',');
|
||||
|
||||
if (cp == NULL)
|
||||
return -1;
|
||||
return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
|
||||
}
|
||||
|
|
|
|||
|
|
@ -172,6 +172,7 @@ static bool interval_count;
|
|||
static const char *output_name;
|
||||
static int output_fd;
|
||||
static int print_free_counters_hint;
|
||||
static int print_mixed_hw_group_error;
|
||||
|
||||
struct perf_stat {
|
||||
bool record;
|
||||
|
|
@ -1126,6 +1127,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
|
|||
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
|
||||
}
|
||||
|
||||
static bool is_mixed_hw_group(struct perf_evsel *counter)
|
||||
{
|
||||
struct perf_evlist *evlist = counter->evlist;
|
||||
u32 pmu_type = counter->attr.type;
|
||||
struct perf_evsel *pos;
|
||||
|
||||
if (counter->nr_members < 2)
|
||||
return false;
|
||||
|
||||
evlist__for_each_entry(evlist, pos) {
|
||||
/* software events can be part of any hardware group */
|
||||
if (pos->attr.type == PERF_TYPE_SOFTWARE)
|
||||
continue;
|
||||
if (pmu_type == PERF_TYPE_SOFTWARE) {
|
||||
pmu_type = pos->attr.type;
|
||||
continue;
|
||||
}
|
||||
if (pmu_type != pos->attr.type)
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
static void printout(int id, int nr, struct perf_evsel *counter, double uval,
|
||||
char *prefix, u64 run, u64 ena, double noise,
|
||||
struct runtime_stat *st)
|
||||
|
|
@ -1178,8 +1203,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
|
|||
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
|
||||
csv_sep);
|
||||
|
||||
if (counter->supported)
|
||||
if (counter->supported) {
|
||||
print_free_counters_hint = 1;
|
||||
if (is_mixed_hw_group(counter))
|
||||
print_mixed_hw_group_error = 1;
|
||||
}
|
||||
|
||||
fprintf(stat_config.output, "%-*s%s",
|
||||
csv_output ? 0 : unit_width,
|
||||
|
|
@ -1256,7 +1284,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
|
|||
char *new_name;
|
||||
char *config;
|
||||
|
||||
if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
|
||||
if (counter->uniquified_name ||
|
||||
!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
|
||||
strlen(counter->pmu_name)))
|
||||
return;
|
||||
|
||||
|
|
@ -1274,6 +1303,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
|
|||
counter->name = new_name;
|
||||
}
|
||||
}
|
||||
|
||||
counter->uniquified_name = true;
|
||||
}
|
||||
|
||||
static void collect_all_aliases(struct perf_evsel *counter,
|
||||
|
|
@ -1757,6 +1788,11 @@ static void print_footer(void)
|
|||
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
|
||||
" perf stat ...\n"
|
||||
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
|
||||
|
||||
if (print_mixed_hw_group_error)
|
||||
fprintf(output,
|
||||
"The events in group usually have to be from "
|
||||
"the same PMU. Try reorganizing the group.\n");
|
||||
}
|
||||
|
||||
static void print_counters(struct timespec *ts, int argc, const char **argv)
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
Family-model,Version,Filename,EventType
|
||||
209[78],1,cf_z10,core
|
||||
281[78],1,cf_z196,core
|
||||
282[78],1,cf_zec12,core
|
||||
296[45],1,cf_z13,core
|
||||
3906,3,cf_z14,core
|
||||
^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core
|
||||
^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core
|
||||
^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
|
||||
^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
|
||||
^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
|
||||
|
|
|
|||
|
|
|
@ -35,3 +35,6 @@ inherit=0
|
|||
# sampling disabled
|
||||
sample_freq=0
|
||||
sample_period=0
|
||||
freq=0
|
||||
write_backward=0
|
||||
sample_id_all=0
|
||||
|
|
|
|||
|
|
@ -19,12 +19,10 @@ trace_libc_inet_pton_backtrace() {
|
|||
expected[1]=".*inet_pton[[:space:]]\($libc\)$"
|
||||
case "$(uname -m)" in
|
||||
s390x)
|
||||
eventattr='call-graph=dwarf'
|
||||
eventattr='call-graph=dwarf,max-stack=4'
|
||||
expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
|
||||
expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
|
||||
expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$"
|
||||
expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
|
||||
expected[5]="__libc_start_main[[:space:]]\($libc\)$"
|
||||
expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$"
|
||||
;;
|
||||
*)
|
||||
eventattr='max-stack=3'
|
||||
|
|
|
|||
|
|
@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
|
|||
* than leader in case leader 'leads' the sampling.
|
||||
*/
|
||||
if ((leader != evsel) && leader->sample_read) {
|
||||
attr->sample_freq = 0;
|
||||
attr->sample_period = 0;
|
||||
attr->freq = 0;
|
||||
attr->sample_freq = 0;
|
||||
attr->sample_period = 0;
|
||||
attr->write_backward = 0;
|
||||
attr->sample_id_all = 0;
|
||||
}
|
||||
|
||||
if (opts->no_samples)
|
||||
|
|
@ -1922,7 +1925,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
|||
goto fallback_missing_features;
|
||||
} else if (!perf_missing_features.group_read &&
|
||||
evsel->attr.inherit &&
|
||||
(evsel->attr.read_format & PERF_FORMAT_GROUP)) {
|
||||
(evsel->attr.read_format & PERF_FORMAT_GROUP) &&
|
||||
perf_evsel__is_group_leader(evsel)) {
|
||||
perf_missing_features.group_read = true;
|
||||
pr_debug2("switching off group read\n");
|
||||
goto fallback_missing_features;
|
||||
|
|
@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
|
|||
(paranoid = perf_event_paranoid()) > 1) {
|
||||
const char *name = perf_evsel__name(evsel);
|
||||
char *new_name;
|
||||
const char *sep = ":";
|
||||
|
||||
if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
|
||||
/* Is there already the separator in the name. */
|
||||
if (strchr(name, '/') ||
|
||||
strchr(name, ':'))
|
||||
sep = "";
|
||||
|
||||
if (asprintf(&new_name, "%s%su", name, sep) < 0)
|
||||
return false;
|
||||
|
||||
if (evsel->name)
|
||||
|
|
|
|||
|
|
@ -115,6 +115,7 @@ struct perf_evsel {
|
|||
unsigned int sample_size;
|
||||
int id_pos;
|
||||
int is_pos;
|
||||
bool uniquified_name;
|
||||
bool snapshot;
|
||||
bool supported;
|
||||
bool needs_swap;
|
||||
|
|
|
|||
|
|
@ -1019,13 +1019,6 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
|
|||
return ret;
|
||||
}
|
||||
|
||||
static void map_groups__fixup_end(struct map_groups *mg)
|
||||
{
|
||||
int i;
|
||||
for (i = 0; i < MAP__NR_TYPES; ++i)
|
||||
__map_groups__fixup_end(mg, i);
|
||||
}
|
||||
|
||||
static char *get_kernel_version(const char *root_dir)
|
||||
{
|
||||
char version[PATH_MAX];
|
||||
|
|
@ -1233,6 +1226,7 @@ int machine__create_kernel_maps(struct machine *machine)
|
|||
{
|
||||
struct dso *kernel = machine__get_kernel(machine);
|
||||
const char *name = NULL;
|
||||
struct map *map;
|
||||
u64 addr = 0;
|
||||
int ret;
|
||||
|
||||
|
|
@ -1259,13 +1253,25 @@ int machine__create_kernel_maps(struct machine *machine)
|
|||
machine__destroy_kernel_maps(machine);
|
||||
return -1;
|
||||
}
|
||||
machine__set_kernel_mmap(machine, addr, 0);
|
||||
|
||||
/* we have a real start address now, so re-order the kmaps */
|
||||
map = machine__kernel_map(machine);
|
||||
|
||||
map__get(map);
|
||||
map_groups__remove(&machine->kmaps, map);
|
||||
|
||||
/* assume it's the last in the kmaps */
|
||||
machine__set_kernel_mmap(machine, addr, ~0ULL);
|
||||
|
||||
map_groups__insert(&machine->kmaps, map);
|
||||
map__put(map);
|
||||
}
|
||||
|
||||
/*
|
||||
* Now that we have all the maps created, just set the ->end of them:
|
||||
*/
|
||||
map_groups__fixup_end(&machine->kmaps);
|
||||
/* update end address of the kernel map using adjacent module address */
|
||||
map = map__next(machine__kernel_map(machine));
|
||||
if (map)
|
||||
machine__set_kernel_mmap(machine, addr, map->start);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -224,15 +224,15 @@ event_def: event_pmu |
|
|||
event_bpf_file
|
||||
|
||||
event_pmu:
|
||||
PE_NAME opt_event_config
|
||||
PE_NAME '/' event_config '/'
|
||||
{
|
||||
struct list_head *list, *orig_terms, *terms;
|
||||
|
||||
if (parse_events_copy_term_list($2, &orig_terms))
|
||||
if (parse_events_copy_term_list($3, &orig_terms))
|
||||
YYABORT;
|
||||
|
||||
ALLOC_LIST(list);
|
||||
if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
|
||||
if (parse_events_add_pmu(_parse_state, list, $1, $3, false)) {
|
||||
struct perf_pmu *pmu = NULL;
|
||||
int ok = 0;
|
||||
char *pattern;
|
||||
|
|
@ -262,7 +262,7 @@ PE_NAME opt_event_config
|
|||
if (!ok)
|
||||
YYABORT;
|
||||
}
|
||||
parse_events_terms__delete($2);
|
||||
parse_events_terms__delete($3);
|
||||
parse_events_terms__delete(orig_terms);
|
||||
$$ = list;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name)
|
|||
|
||||
/*
|
||||
* PMU CORE devices have different name other than cpu in sysfs on some
|
||||
* platforms. looking for possible sysfs files to identify as core device.
|
||||
* platforms.
|
||||
* Looking for possible sysfs files to identify the arm core device.
|
||||
*/
|
||||
static int is_pmu_core(const char *name)
|
||||
static int is_arm_pmu_core(const char *name)
|
||||
{
|
||||
struct stat st;
|
||||
char path[PATH_MAX];
|
||||
|
|
@ -550,12 +551,6 @@ static int is_pmu_core(const char *name)
|
|||
if (!sysfs)
|
||||
return 0;
|
||||
|
||||
/* Look for cpu sysfs (x86 and others) */
|
||||
scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
|
||||
if ((stat(path, &st) == 0) &&
|
||||
(strncmp(name, "cpu", strlen("cpu")) == 0))
|
||||
return 1;
|
||||
|
||||
/* Look for cpu sysfs (specific to arm) */
|
||||
scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
|
||||
sysfs, name);
|
||||
|
|
@ -586,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
|
|||
* cpuid string generated on this platform.
|
||||
* Otherwise return non-zero.
|
||||
*/
|
||||
int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
|
||||
int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
|
||||
{
|
||||
regex_t re;
|
||||
regmatch_t pmatch[1];
|
||||
|
|
@ -668,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
|
|||
struct pmu_events_map *map;
|
||||
struct pmu_event *pe;
|
||||
const char *name = pmu->name;
|
||||
const char *pname;
|
||||
|
||||
map = perf_pmu__find_map(pmu);
|
||||
if (!map)
|
||||
|
|
@ -686,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
|
|||
break;
|
||||
}
|
||||
|
||||
if (!is_pmu_core(name)) {
|
||||
/* check for uncore devices */
|
||||
if (pe->pmu == NULL)
|
||||
continue;
|
||||
if (strncmp(pe->pmu, name, strlen(pe->pmu)))
|
||||
if (!is_arm_pmu_core(name)) {
|
||||
pname = pe->pmu ? pe->pmu : "cpu";
|
||||
if (strncmp(pname, name, strlen(pname)))
|
||||
continue;
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user