Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-11 14:42:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf tools: Add machine_pid and vcpu to id_index

Browse Source 
When injecting events from a guest perf.data file, the events will have
separate sample ID numbers. These ID numbers can then be used to determine
which machine an event belongs to. To facilitate that, add machine_pid and
vcpu to id_index records. For backward compatibility, these are added at
the end of the record, and the length of the record is used to determine
if they are present or not.

Note, this is needed because the events from a guest perf.data file contain
the pid/tid of the process running at that time inside the VM not the
pid/tid of the (QEMU) hypervisor thread. So a way is needed to relate
guest events back to the guest machine and VCPU, and using sample ID
numbers for that is relatively simple and convenient.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: kvm@vger.kernel.org
Link: https://lore.kernel.org/r/20220711093218.10967-11-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Adrian Hunter 2022-07-11 12:31:53 +03:00 committed by Arnaldo Carvalho de Melo
parent c1fd5b7d8a
commit b47bb18661
5 changed files with 84 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tools/lib/perf/include/internal/evsel.h
View File

@ -30,6 +30,10 @@ struct perf_sample_id {
struct perf_cpu cpu;
pid_t tid;
/* Guest machine pid and VCPU, valid only if machine_pid is non-zero */
pid_t machine_pid;
struct perf_cpu vcpu;
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
u64 period;
};

5
tools/lib/perf/include/perf/event.h
View File

@ -237,6 +237,11 @@ struct id_index_entry {
__u64 tid;
};
struct id_index_entry_2 {
__u64 machine_pid;
__u64 vcpu;
};
struct perf_record_id_index {
struct perf_event_header header;
__u64 nr;

40
tools/perf/util/session.c
View File

@ -2756,18 +2756,35 @@ int perf_event__process_id_index(struct perf_session *session,
{
struct evlist *evlist = session->evlist;
struct perf_record_id_index *ie = &event->id_index;
size_t sz = ie->header.size - sizeof(*ie);
size_t i, nr, max_nr;
size_t e1_sz = sizeof(struct id_index_entry);
size_t e2_sz = sizeof(struct id_index_entry_2);
size_t etot_sz = e1_sz + e2_sz;
struct id_index_entry_2 *e2;
max_nr = (ie->header.size - sizeof(struct perf_record_id_index)) /
sizeof(struct id_index_entry);
max_nr = sz / e1_sz;
nr = ie->nr;
if (nr > max_nr)
if (nr > max_nr) {
printf("Too big: nr %zu max_nr %zu\n", nr, max_nr);
return -EINVAL;
}
if (sz >= nr * etot_sz) {
max_nr = sz / etot_sz;
if (nr > max_nr) {
printf("Too big2: nr %zu max_nr %zu\n", nr, max_nr);
return -EINVAL;
}
e2 = (void *)ie + sizeof(*ie) + nr * e1_sz;
} else {
e2 = NULL;
}
if (dump_trace)
fprintf(stdout, " nr: %zu\n", nr);
for (i = 0; i < nr; i++) {
for (i = 0; i < nr; i++, (e2 ? e2++ : 0)) {
struct id_index_entry *e = &ie->entries[i];
struct perf_sample_id *sid;
@ -2775,15 +2792,28 @@ int perf_event__process_id_index(struct perf_session *session,
fprintf(stdout, " ... id: %"PRI_lu64, e->id);
fprintf(stdout, " idx: %"PRI_lu64, e->idx);
fprintf(stdout, " cpu: %"PRI_ld64, e->cpu);
fprintf(stdout, " tid: %"PRI_ld64"\n", e->tid);
fprintf(stdout, " tid: %"PRI_ld64, e->tid);
if (e2) {
fprintf(stdout, " machine_pid: %"PRI_ld64, e2->machine_pid);
fprintf(stdout, " vcpu: %"PRI_lu64"\n", e2->vcpu);
} else {
fprintf(stdout, "\n");
}
}
sid = evlist__id2sid(evlist, e->id);
if (!sid)
return -ENOENT;
sid->idx = e->idx;
sid->cpu.cpu = e->cpu;
sid->tid = e->tid;
if (!e2)
continue;
sid->machine_pid = e2->machine_pid;
sid->vcpu.cpu = e2->vcpu;
}
return 0;
}

51
tools/perf/util/synthetic-events.c
View File

@ -1759,19 +1759,26 @@ int perf_event__synthesize_id_sample(__u64 *array, u64 type, const struct perf_s
return (void *)array - (void *)start;
}
int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
struct evlist *evlist, struct machine *machine)
int __perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
struct evlist *evlist, struct machine *machine, size_t from)
{
union perf_event *ev;
struct evsel *evsel;
size_t nr = 0, i = 0, sz, max_nr, n;
size_t nr = 0, i = 0, sz, max_nr, n, pos;
size_t e1_sz = sizeof(struct id_index_entry);
size_t e2_sz = sizeof(struct id_index_entry_2);
size_t etot_sz = e1_sz + e2_sz;
bool e2_needed = false;
int err;
max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) /
sizeof(struct id_index_entry);
max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) / etot_sz;
evlist__for_each_entry(evlist, evsel)
pos = 0;
evlist__for_each_entry(evlist, evsel) {
if (pos++ < from)
continue;
nr += evsel->core.ids;
}
if (!nr)
return 0;
@ -1779,31 +1786,38 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
pr_debug2("Synthesizing id index\n");
n = nr > max_nr ? max_nr : nr;
sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry);
sz = sizeof(struct perf_record_id_index) + n * etot_sz;
ev = zalloc(sz);
if (!ev)
return -ENOMEM;
sz = sizeof(struct perf_record_id_index) + n * e1_sz;
ev->id_index.header.type = PERF_RECORD_ID_INDEX;
ev->id_index.header.size = sz;
ev->id_index.nr = n;
pos = 0;
evlist__for_each_entry(evlist, evsel) {
u32 j;
for (j = 0; j < evsel->core.ids; j++) {
if (pos++ < from)
continue;
for (j = 0; j < evsel->core.ids; j++, i++) {
struct id_index_entry *e;
struct id_index_entry_2 *e2;
struct perf_sample_id *sid;
if (i >= n) {
ev->id_index.header.size = sz + (e2_needed ? n * e2_sz : 0);
err = process(tool, ev, NULL, machine);
if (err)
goto out_err;
nr -= n;
i = 0;
e2_needed = false;
}
e = &ev->id_index.entries[i++];
e = &ev->id_index.entries[i];
e->id = evsel->core.id[j];
@ -1816,11 +1830,18 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
e->idx = sid->idx;
e->cpu = sid->cpu.cpu;
e->tid = sid->tid;
if (sid->machine_pid)
e2_needed = true;
e2 = (void *)ev + sz;
e2[i].machine_pid = sid->machine_pid;
e2[i].vcpu = sid->vcpu.cpu;
}
}
sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry);
ev->id_index.header.size = sz;
sz = sizeof(struct perf_record_id_index) + nr * e1_sz;
ev->id_index.header.size = sz + (e2_needed ? nr * e2_sz : 0);
ev->id_index.nr = nr;
err = process(tool, ev, NULL, machine);
@ -1830,6 +1851,12 @@ out_err:
return err;
}
int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
struct evlist *evlist, struct machine *machine)
{
return __perf_event__synthesize_id_index(tool, process, evlist, machine, 0);
}
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct perf_thread_map *threads,
perf_event__handler_t process, bool needs_mmap,

1
tools/perf/util/synthetic-events.h
View File

@ -55,6 +55,7 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evs
int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process);
int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine);
int __perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine, size_t from);
int perf_event__synthesize_id_sample(__u64 *array, u64 type, const struct perf_sample *sample);
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);