aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/annotate.c38
-rw-r--r--tools/perf/util/annotate.h1
-rw-r--r--tools/perf/util/build-id.c10
-rw-r--r--tools/perf/util/cgroup.c17
-rw-r--r--tools/perf/util/cs-etm-decoder/cs-etm-decoder.c74
-rw-r--r--tools/perf/util/cs-etm-decoder/cs-etm-decoder.h2
-rw-r--r--tools/perf/util/cs-etm.c478
-rw-r--r--tools/perf/util/event.c16
-rw-r--r--tools/perf/util/evlist.c46
-rw-r--r--tools/perf/util/evlist.h4
-rw-r--r--tools/perf/util/evsel.c3
-rw-r--r--tools/perf/util/header.h1
-rw-r--r--tools/perf/util/hist.c4
-rw-r--r--tools/perf/util/hist.h1
-rw-r--r--tools/perf/util/machine.c145
-rw-r--r--tools/perf/util/machine.h6
-rw-r--r--tools/perf/util/mmap.c21
-rw-r--r--tools/perf/util/pmu.c47
-rw-r--r--tools/perf/util/python.c107
-rw-r--r--tools/perf/util/record.c43
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c147
-rw-r--r--tools/perf/util/setup.py6
-rw-r--r--tools/perf/util/sort.c7
-rw-r--r--tools/perf/util/stat.h2
-rw-r--r--tools/perf/util/symbol.c13
-rw-r--r--tools/perf/util/syscalltbl.c8
-rw-r--r--tools/perf/util/thread_map.c5
-rw-r--r--tools/perf/util/thread_map.h3
28 files changed, 914 insertions, 341 deletions
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28b233c3dcbe..49ff825f745c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -187,6 +187,9 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
{
char *endptr, *tok, *name;
+ struct addr_map_symbol target = {
+ .map = map,
+ };
ops->target.addr = strtoull(ops->raw, &endptr, 16);
@@ -208,28 +211,29 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *
ops->target.name = strdup(name);
*tok = '>';
- return ops->target.name == NULL ? -1 : 0;
+ if (ops->target.name == NULL)
+ return -1;
+find_target:
+ target.addr = map__objdump_2mem(map, ops->target.addr);
-indirect_call:
- tok = strchr(endptr, '*');
- if (tok == NULL) {
- struct symbol *sym = map__find_symbol(map, map->map_ip(map, ops->target.addr));
- if (sym != NULL)
- ops->target.name = strdup(sym->name);
- else
- ops->target.addr = 0;
- return 0;
- }
+ if (map_groups__find_ams(&target) == 0 &&
+ map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+ ops->target.sym = target.sym;
- ops->target.addr = strtoull(tok + 1, NULL, 16);
return 0;
+
+indirect_call:
+ tok = strchr(endptr, '*');
+ if (tok != NULL)
+ ops->target.addr = strtoull(tok + 1, NULL, 16);
+ goto find_target;
}
static int call__scnprintf(struct ins *ins, char *bf, size_t size,
struct ins_operands *ops)
{
- if (ops->target.name)
- return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
+ if (ops->target.sym)
+ return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
if (ops->target.addr == 0)
return ins__raw_scnprintf(ins, bf, size, ops);
@@ -1283,8 +1287,8 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
dl->ops.target.offset_avail = true;
}
- /* kcore has no symbols, so add the call target name */
- if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) {
+ /* kcore has no symbols, so add the call target symbol */
+ if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
struct addr_map_symbol target = {
.map = map,
.addr = dl->ops.target.addr,
@@ -1292,7 +1296,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
if (!map_groups__find_ams(&target) &&
target.sym->start == target.al_addr)
- dl->ops.target.name = strdup(target.sym->name);
+ dl->ops.target.sym = target.sym;
}
annotation_line__add(&dl->al, &notes->src->source);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index ce427445671f..7e914e834101 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -24,6 +24,7 @@ struct ins_operands {
struct {
char *raw;
char *name;
+ struct symbol *sym;
u64 addr;
s64 offset;
bool offset_avail;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 7f8553630c4d..537eadd81914 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -316,7 +316,6 @@ static int machine__write_buildid_table(struct machine *machine,
struct feat_fd *fd)
{
int err = 0;
- char nm[PATH_MAX];
struct dso *pos;
u16 kmisc = PERF_RECORD_MISC_KERNEL,
umisc = PERF_RECORD_MISC_USER;
@@ -338,9 +337,8 @@ static int machine__write_buildid_table(struct machine *machine,
name = pos->short_name;
name_len = pos->short_name_len;
} else if (dso__is_kcore(pos)) {
- machine__mmap_name(machine, nm, sizeof(nm));
- name = nm;
- name_len = strlen(nm);
+ name = machine->mmap_name;
+ name_len = strlen(name);
} else {
name = pos->long_name;
name_len = pos->long_name_len;
@@ -813,12 +811,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
bool is_kallsyms = dso__is_kallsyms(dso);
bool is_vdso = dso__is_vdso(dso);
const char *name = dso->long_name;
- char nm[PATH_MAX];
if (dso__is_kcore(dso)) {
is_kallsyms = true;
- machine__mmap_name(machine, nm, sizeof(nm));
- name = nm;
+ name = machine->mmap_name;
}
return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
dso->nsinfo, is_kallsyms, is_vdso);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 984f69144f87..5dd9b5ea314d 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -157,9 +157,11 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
int unset __maybe_unused)
{
struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+ struct perf_evsel *counter;
+ struct cgroup_sel *cgrp = NULL;
const char *p, *e, *eos = str + strlen(str);
char *s;
- int ret;
+ int ret, i;
if (list_empty(&evlist->entries)) {
fprintf(stderr, "must define events before cgroups\n");
@@ -188,5 +190,18 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
break;
str = p+1;
}
+ /* for the case one cgroup combine to multiple events */
+ i = 0;
+ if (nr_cgroups == 1) {
+ evlist__for_each_entry(evlist, counter) {
+ if (i == 0)
+ cgrp = counter->cgrp;
+ else {
+ counter->cgrp = cgrp;
+ refcount_inc(&cgrp->refcnt);
+ }
+ i++;
+ }
+ }
return 0;
}
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 1fb01849f1c7..640af88331b4 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -78,6 +78,8 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
{
ocsd_datapath_resp_t dp_ret;
+ decoder->prev_return = OCSD_RESP_CONT;
+
dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
0, 0, NULL, NULL);
if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
@@ -253,16 +255,16 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
decoder->packet_count = 0;
for (i = 0; i < MAX_BUFFER; i++) {
decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
- decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
- decoder->packet_buffer[i].exc = false;
- decoder->packet_buffer[i].exc_ret = false;
- decoder->packet_buffer[i].cpu = INT_MIN;
+ decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+ decoder->packet_buffer[i].last_instr_taken_branch = false;
+ decoder->packet_buffer[i].exc = false;
+ decoder->packet_buffer[i].exc_ret = false;
+ decoder->packet_buffer[i].cpu = INT_MIN;
}
}
static ocsd_datapath_resp_t
cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
- const ocsd_generic_trace_elem *elem,
const u8 trace_chan_id,
enum cs_etm_sample_type sample_type)
{
@@ -278,18 +280,16 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
return OCSD_RESP_FATAL_SYS_ERR;
et = decoder->tail;
+ et = (et + 1) & (MAX_BUFFER - 1);
+ decoder->tail = et;
+ decoder->packet_count++;
+
decoder->packet_buffer[et].sample_type = sample_type;
- decoder->packet_buffer[et].start_addr = elem->st_addr;
- decoder->packet_buffer[et].end_addr = elem->en_addr;
decoder->packet_buffer[et].exc = false;
decoder->packet_buffer[et].exc_ret = false;
decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-
- /* Wrap around if need be */
- et = (et + 1) & (MAX_BUFFER - 1);
-
- decoder->tail = et;
- decoder->packet_count++;
+ decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
+ decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
if (decoder->packet_count == MAX_BUFFER - 1)
return OCSD_RESP_WAIT;
@@ -297,6 +297,47 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
return OCSD_RESP_CONT;
}
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
+ const ocsd_generic_trace_elem *elem,
+ const uint8_t trace_chan_id)
+{
+ int ret = 0;
+ struct cs_etm_packet *packet;
+
+ ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ CS_ETM_RANGE);
+ if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+ return ret;
+
+ packet = &decoder->packet_buffer[decoder->tail];
+
+ packet->start_addr = elem->st_addr;
+ packet->end_addr = elem->en_addr;
+ switch (elem->last_i_type) {
+ case OCSD_INSTR_BR:
+ case OCSD_INSTR_BR_INDIRECT:
+ packet->last_instr_taken_branch = elem->last_instr_exec;
+ break;
+ case OCSD_INSTR_ISB:
+ case OCSD_INSTR_DSB_DMB:
+ case OCSD_INSTR_OTHER:
+ default:
+ packet->last_instr_taken_branch = false;
+ break;
+ }
+
+ return ret;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
+ const uint8_t trace_chan_id)
+{
+ return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ CS_ETM_TRACE_ON);
+}
+
static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
const void *context,
const ocsd_trc_index_t indx __maybe_unused,
@@ -313,12 +354,13 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
decoder->trace_on = false;
break;
case OCSD_GEN_TRC_ELEM_TRACE_ON:
+ resp = cs_etm_decoder__buffer_trace_on(decoder,
+ trace_chan_id);
decoder->trace_on = true;
break;
case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
- resp = cs_etm_decoder__buffer_packet(decoder, elem,
- trace_chan_id,
- CS_ETM_RANGE);
+ resp = cs_etm_decoder__buffer_range(decoder, elem,
+ trace_chan_id);
break;
case OCSD_GEN_TRC_ELEM_EXCEPTION:
decoder->packet_buffer[decoder->tail].exc = true;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 3d2e6205d186..743f5f444304 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -24,12 +24,14 @@ struct cs_etm_buffer {
enum cs_etm_sample_type {
CS_ETM_RANGE = 1 << 0,
+ CS_ETM_TRACE_ON = 1 << 1,
};
struct cs_etm_packet {
enum cs_etm_sample_type sample_type;
u64 start_addr;
u64 end_addr;
+ u8 last_instr_taken_branch;
u8 exc;
u8 exc_ret;
int cpu;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index b9f0a53dfa65..1b0d422373be 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -32,6 +32,14 @@
#define MAX_TIMESTAMP (~0ULL)
+/*
+ * A64 instructions are always 4 bytes
+ *
+ * Only A64 is supported, so can use this constant for converting between
+ * addresses and instruction counts, calculting offsets etc
+ */
+#define A64_INSTR_SIZE 4
+
struct cs_etm_auxtrace {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
@@ -45,11 +53,15 @@ struct cs_etm_auxtrace {
u8 snapshot_mode;
u8 data_queued;
u8 sample_branches;
+ u8 sample_instructions;
int num_cpu;
u32 auxtrace_type;
u64 branches_sample_type;
u64 branches_id;
+ u64 instructions_sample_type;
+ u64 instructions_sample_period;
+ u64 instructions_id;
u64 **metadata;
u64 kernel_start;
unsigned int pmu_type;
@@ -68,6 +80,12 @@ struct cs_etm_queue {
u64 time;
u64 timestamp;
u64 offset;
+ u64 period_instructions;
+ struct branch_stack *last_branch;
+ struct branch_stack *last_branch_rb;
+ size_t last_branch_pos;
+ struct cs_etm_packet *prev_packet;
+ struct cs_etm_packet *packet;
};
static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
@@ -174,6 +192,16 @@ static void cs_etm__free_queue(void *priv)
{
struct cs_etm_queue *etmq = priv;
+ if (!etmq)
+ return;
+
+ thread__zput(etmq->thread);
+ cs_etm_decoder__free(etmq->decoder);
+ zfree(&etmq->event_buf);
+ zfree(&etmq->last_branch);
+ zfree(&etmq->last_branch_rb);
+ zfree(&etmq->prev_packet);
+ zfree(&etmq->packet);
free(etmq);
}
@@ -270,11 +298,35 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
struct cs_etm_decoder_params d_params;
struct cs_etm_trace_params *t_params;
struct cs_etm_queue *etmq;
+ size_t szp = sizeof(struct cs_etm_packet);
etmq = zalloc(sizeof(*etmq));
if (!etmq)
return NULL;
+ etmq->packet = zalloc(szp);
+ if (!etmq->packet)
+ goto out_free;
+
+ if (etm->synth_opts.last_branch || etm->sample_branches) {
+ etmq->prev_packet = zalloc(szp);
+ if (!etmq->prev_packet)
+ goto out_free;
+ }
+
+ if (etm->synth_opts.last_branch) {
+ size_t sz = sizeof(struct branch_stack);
+
+ sz += etm->synth_opts.last_branch_sz *
+ sizeof(struct branch_entry);
+ etmq->last_branch = zalloc(sz);
+ if (!etmq->last_branch)
+ goto out_free;
+ etmq->last_branch_rb = zalloc(sz);
+ if (!etmq->last_branch_rb)
+ goto out_free;
+ }
+
etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
if (!etmq->event_buf)
goto out_free;
@@ -329,6 +381,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
goto out_free_decoder;
etmq->offset = 0;
+ etmq->period_instructions = 0;
return etmq;
@@ -336,6 +389,10 @@ out_free_decoder:
cs_etm_decoder__free(etmq->decoder);
out_free:
zfree(&etmq->event_buf);
+ zfree(&etmq->last_branch);
+ zfree(&etmq->last_branch_rb);
+ zfree(&etmq->prev_packet);
+ zfree(&etmq->packet);
free(etmq);
return NULL;
@@ -389,6 +446,129 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
return 0;
}
+static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq)
+{
+ struct branch_stack *bs_src = etmq->last_branch_rb;
+ struct branch_stack *bs_dst = etmq->last_branch;
+ size_t nr = 0;
+
+ /*
+ * Set the number of records before early exit: ->nr is used to
+ * determine how many branches to copy from ->entries.
+ */
+ bs_dst->nr = bs_src->nr;
+
+ /*
+ * Early exit when there is nothing to copy.
+ */
+ if (!bs_src->nr)
+ return;
+
+ /*
+ * As bs_src->entries is a circular buffer, we need to copy from it in
+ * two steps. First, copy the branches from the most recently inserted
+ * branch ->last_branch_pos until the end of bs_src->entries buffer.
+ */
+ nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos;
+ memcpy(&bs_dst->entries[0],
+ &bs_src->entries[etmq->last_branch_pos],
+ sizeof(struct branch_entry) * nr);
+
+ /*
+ * If we wrapped around at least once, the branches from the beginning
+ * of the bs_src->entries buffer and until the ->last_branch_pos element
+ * are older valid branches: copy them over. The total number of
+ * branches copied over will be equal to the number of branches asked by
+ * the user in last_branch_sz.
+ */
+ if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
+ memcpy(&bs_dst->entries[nr],
+ &bs_src->entries[0],
+ sizeof(struct branch_entry) * etmq->last_branch_pos);
+ }
+}
+
+static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
+{
+ etmq->last_branch_pos = 0;
+ etmq->last_branch_rb->nr = 0;
+}
+
+static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
+{
+ /*
+ * The packet records the execution range with an exclusive end address
+ *
+ * A64 instructions are constant size, so the last executed
+ * instruction is A64_INSTR_SIZE before the end address
+ * Will need to do instruction level decode for T32 instructions as
+ * they can be variable size (not yet supported).
+ */
+ return packet->end_addr - A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
+{
+ /*
+ * Only A64 instructions are currently supported, so can get
+ * instruction count by dividing.
+ * Will need to do instruction level decode for T32 instructions as
+ * they can be variable size (not yet supported).
+ */
+ return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet,
+ u64 offset)
+{
+ /*
+ * Only A64 instructions are currently supported, so can get
+ * instruction address by muliplying.
+ * Will need to do instruction level decode for T32 instructions as
+ * they can be variable size (not yet supported).
+ */
+ return packet->start_addr + offset * A64_INSTR_SIZE;
+}
+
+static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
+{
+ struct branch_stack *bs = etmq->last_branch_rb;
+ struct branch_entry *be;
+
+ /*
+ * The branches are recorded in a circular buffer in reverse
+ * chronological order: we start recording from the last element of the
+ * buffer down. After writing the first element of the stack, move the
+ * insert position back to the end of the buffer.
+ */
+ if (!etmq->last_branch_pos)
+ etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
+
+ etmq->last_branch_pos -= 1;
+
+ be = &bs->entries[etmq->last_branch_pos];
+ be->from = cs_etm__last_executed_instr(etmq->prev_packet);
+ be->to = etmq->packet->start_addr;
+ /* No support for mispredict */
+ be->flags.mispred = 0;
+ be->flags.predicted = 1;
+
+ /*
+ * Increment bs->nr until reaching the number of last branches asked by
+ * the user on the command line.
+ */
+ if (bs->nr < etmq->etm->synth_opts.last_branch_sz)
+ bs->nr += 1;
+}
+
+static int cs_etm__inject_event(union perf_event *event,
+ struct perf_sample *sample, u64 type)
+{
+ event->header.size = perf_event__sample_event_size(sample, type, 0);
+ return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
+
static int
cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
{
@@ -453,35 +633,105 @@ static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
}
}
+static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
+ u64 addr, u64 period)
+{
+ int ret = 0;
+ struct cs_etm_auxtrace *etm = etmq->etm;
+ union perf_event *event = etmq->event_buf;
+ struct perf_sample sample = {.ip = 0,};
+
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.misc = PERF_RECORD_MISC_USER;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ sample.ip = addr;
+ sample.pid = etmq->pid;
+ sample.tid = etmq->tid;
+ sample.id = etmq->etm->instructions_id;
+ sample.stream_id = etmq->etm->instructions_id;
+ sample.period = period;
+ sample.cpu = etmq->packet->cpu;
+ sample.flags = 0;
+ sample.insn_len = 1;
+ sample.cpumode = event->header.misc;
+
+ if (etm->synth_opts.last_branch) {
+ cs_etm__copy_last_branch_rb(etmq);
+ sample.branch_stack = etmq->last_branch;
+ }
+
+ if (etm->synth_opts.inject) {
+ ret = cs_etm__inject_event(event, &sample,
+ etm->instructions_sample_type);
+ if (ret)
+ return ret;
+ }
+
+ ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+ if (ret)
+ pr_err(
+ "CS ETM Trace: failed to deliver instruction event, error %d\n",
+ ret);
+
+ if (etm->synth_opts.last_branch)
+ cs_etm__reset_last_branch_rb(etmq);
+
+ return ret;
+}
+
/*
* The cs etm packet encodes an instruction range between a branch target
* and the next taken branch. Generate sample accordingly.
*/
-static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
- struct cs_etm_packet *packet)
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
{
int ret = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
struct perf_sample sample = {.ip = 0,};
union perf_event *event = etmq->event_buf;
- u64 start_addr = packet->start_addr;
- u64 end_addr = packet->end_addr;
+ struct dummy_branch_stack {
+ u64 nr;
+ struct branch_entry entries;
+ } dummy_bs;
event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = PERF_RECORD_MISC_USER;
event->sample.header.size = sizeof(struct perf_event_header);
- sample.ip = start_addr;
+ sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
sample.pid = etmq->pid;
sample.tid = etmq->tid;
- sample.addr = end_addr;
+ sample.addr = etmq->packet->start_addr;
sample.id = etmq->etm->branches_id;
sample.stream_id = etmq->etm->branches_id;
sample.period = 1;
- sample.cpu = packet->cpu;
+ sample.cpu = etmq->packet->cpu;
sample.flags = 0;
sample.cpumode = PERF_RECORD_MISC_USER;
+ /*
+ * perf report cannot handle events without a branch stack
+ */
+ if (etm->synth_opts.last_branch) {
+ dummy_bs = (struct dummy_branch_stack){
+ .nr = 1,
+ .entries = {
+ .from = sample.ip,
+ .to = sample.addr,
+ },
+ };
+ sample.branch_stack = (struct branch_stack *)&dummy_bs;
+ }
+
+ if (etm->synth_opts.inject) {
+ ret = cs_etm__inject_event(event, &sample,
+ etm->branches_sample_type);
+ if (ret)
+ return ret;
+ }
+
ret = perf_session__deliver_synth_event(etm->session, event, &sample);
if (ret)
@@ -578,6 +828,24 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
etm->sample_branches = true;
etm->branches_sample_type = attr.sample_type;
etm->branches_id = id;
+ id += 1;
+ attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
+ }
+
+ if (etm->synth_opts.last_branch)
+ attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+
+ if (etm->synth_opts.instructions) {
+ attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+ attr.sample_period = etm->synth_opts.period;
+ etm->instructions_sample_period = attr.sample_period;
+ err = cs_etm__synth_event(session, &attr, id);
+ if (err)
+ return err;
+ etm->sample_instructions = true;
+ etm->instructions_sample_type = attr.sample_type;
+ etm->instructions_id = id;
+ id += 1;
}
return 0;
@@ -585,25 +853,108 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
static int cs_etm__sample(struct cs_etm_queue *etmq)
{
+ struct cs_etm_auxtrace *etm = etmq->etm;
+ struct cs_etm_packet *tmp;
int ret;
- struct cs_etm_packet packet;
+ u64 instrs_executed;
- while (1) {
- ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
- if (ret <= 0)
+ instrs_executed = cs_etm__instr_count(etmq->packet);
+ etmq->period_instructions += instrs_executed;
+
+ /*
+ * Record a branch when the last instruction in
+ * PREV_PACKET is a branch.
+ */
+ if (etm->synth_opts.last_branch &&
+ etmq->prev_packet &&
+ etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+ etmq->prev_packet->last_instr_taken_branch)
+ cs_etm__update_last_branch_rb(etmq);
+
+ if (etm->sample_instructions &&
+ etmq->period_instructions >= etm->instructions_sample_period) {
+ /*
+ * Emit instruction sample periodically
+ * TODO: allow period to be defined in cycles and clock time
+ */
+
+ /* Get number of instructions executed after the sample point */
+ u64 instrs_over = etmq->period_instructions -
+ etm->instructions_sample_period;
+
+ /*
+ * Calculate the address of the sampled instruction (-1 as
+ * sample is reported as though instruction has just been
+ * executed, but PC has not advanced to next instruction)
+ */
+ u64 offset = (instrs_executed - instrs_over - 1);
+ u64 addr = cs_etm__instr_addr(etmq->packet, offset);
+
+ ret = cs_etm__synth_instruction_sample(
+ etmq, addr, etm->instructions_sample_period);
+ if (ret)
+ return ret;
+
+ /* Carry remaining instructions into next sample period */
+ etmq->period_instructions = instrs_over;
+ }
+
+ if (etm->sample_branches &&
+ etmq->prev_packet &&
+ etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+ etmq->prev_packet->last_instr_taken_branch) {
+ ret = cs_etm__synth_branch_sample(etmq);
+ if (ret)
return ret;
+ }
+ if (etm->sample_branches || etm->synth_opts.last_branch) {
/*
- * If the packet contains an instruction range, generate an
- * instruction sequence event.
+ * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+ * the next incoming packet.
*/
- if (packet.sample_type & CS_ETM_RANGE)
- cs_etm__synth_branch_sample(etmq, &packet);
+ tmp = etmq->packet;
+ etmq->packet = etmq->prev_packet;
+ etmq->prev_packet = tmp;
}
return 0;
}
+static int cs_etm__flush(struct cs_etm_queue *etmq)
+{
+ int err = 0;
+ struct cs_etm_packet *tmp;
+
+ if (etmq->etm->synth_opts.last_branch &&
+ etmq->prev_packet &&
+ etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+ /*
+ * Generate a last branch event for the branches left in the
+ * circular buffer at the end of the trace.
+ *
+ * Use the address of the end of the last reported execution
+ * range
+ */
+ u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+
+ err = cs_etm__synth_instruction_sample(
+ etmq, addr,
+ etmq->period_instructions);
+ etmq->period_instructions = 0;
+
+ /*
+ * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+ * the next incoming packet.
+ */
+ tmp = etmq->packet;
+ etmq->packet = etmq->prev_packet;
+ etmq->prev_packet = tmp;
+ }
+
+ return err;
+}
+
static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
{
struct cs_etm_auxtrace *etm = etmq->etm;
@@ -615,45 +966,72 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
etm->kernel_start = machine__kernel_start(etm->machine);
/* Go through each buffer in the queue and decode them one by one */
-more:
- buffer_used = 0;
- memset(&buffer, 0, sizeof(buffer));
- err = cs_etm__get_trace(&buffer, etmq);
- if (err <= 0)
- return err;
- /*
- * We cannot assume consecutive blocks in the data file are contiguous,
- * reset the decoder to force re-sync.
- */
- err = cs_etm_decoder__reset(etmq->decoder);
- if (err != 0)
- return err;
-
- /* Run trace decoder until buffer consumed or end of trace */
- do {
- processed = 0;
-
- err = cs_etm_decoder__process_data_block(
- etmq->decoder,
- etmq->offset,
- &buffer.buf[buffer_used],
- buffer.len - buffer_used,
- &processed);
-
- if (err)
+ while (1) {
+ buffer_used = 0;
+ memset(&buffer, 0, sizeof(buffer));
+ err = cs_etm__get_trace(&buffer, etmq);
+ if (err <= 0)
return err;
-
- etmq->offset += processed;
- buffer_used += processed;
-
/*
- * Nothing to do with an error condition, let's hope the next
- * chunk will be better.
+ * We cannot assume consecutive blocks in the data file are
+ * contiguous, reset the decoder to force re-sync.
*/
- err = cs_etm__sample(etmq);
- } while (buffer.len > buffer_used);
+ err = cs_etm_decoder__reset(etmq->decoder);
+ if (err != 0)
+ return err;
+
+ /* Run trace decoder until buffer consumed or end of trace */
+ do {
+ processed = 0;
+ err = cs_etm_decoder__process_data_block(
+ etmq->decoder,
+ etmq->offset,
+ &buffer.buf[buffer_used],
+ buffer.len - buffer_used,
+ &processed);
+ if (err)
+ return err;
+
+ etmq->offset += processed;
+ buffer_used += processed;
+
+ /* Process each packet in this chunk */
+ while (1) {
+ err = cs_etm_decoder__get_packet(etmq->decoder,
+ etmq->packet);
+ if (err <= 0)
+ /*
+ * Stop processing this chunk on
+ * end of data or error
+ */
+ break;
+
+ switch (etmq->packet->sample_type) {
+ case CS_ETM_RANGE:
+ /*
+ * If the packet contains an instruction
+ * range, generate instruction sequence
+ * events.
+ */
+ cs_etm__sample(etmq);
+ break;
+ case CS_ETM_TRACE_ON:
+ /*
+ * Discontinuity in trace, flush
+ * previous branch stack
+ */
+ cs_etm__flush(etmq);
+ break;
+ default:
+ break;
+ }
+ }
+ } while (buffer.len > buffer_used);
-goto more;
+ if (err == 0)
+ /* Flush any remaining branch stack entries */
+ err = cs_etm__flush(etmq);
+ }
return err;
}
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 44e603c27944..f0a6cbd033cc 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -894,8 +894,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
struct machine *machine)
{
size_t size;
- const char *mmap_name;
- char name_buff[PATH_MAX];
struct map *map = machine__kernel_map(machine);
struct kmap *kmap;
int err;
@@ -918,7 +916,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
return -1;
}
- mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
if (machine__is_host(machine)) {
/*
* kernel uses PERF_RECORD_MISC_USER for user space maps,
@@ -931,7 +928,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
kmap = map__kmap(map);
size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
- "%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
+ "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
size = PERF_ALIGN(size, sizeof(u64));
event->mmap.header.type = PERF_RECORD_MMAP;
event->mmap.header.size = (sizeof(event->mmap) -
@@ -1591,17 +1588,6 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
return -1;
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
- /*
- * Have we already created the kernel maps for this machine?
- *
- * This should have happened earlier, when we processed the kernel MMAP
- * events, but for older perf.data files there was no such thing, so do
- * it now.
- */
- if (sample->cpumode == PERF_RECORD_MISC_KERNEL &&
- machine__kernel_map(machine) == NULL)
- machine__create_kernel_maps(machine);
-
thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
dump_printf(" ...... dso: %s\n",
al->map ? al->map->dso->long_name :
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e5fc14e53c05..41a4666f1519 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -702,29 +702,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
return perf_evlist__set_paused(evlist, false);
}
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
-{
- struct perf_mmap *md = &evlist->mmap[idx];
-
- /*
- * Check messup is required for forward overwritable ring buffer:
- * memory pointed by md->prev can be overwritten in this case.
- * No need for read-write ring buffer: kernel stop outputting when
- * it hit md->prev (perf_mmap__consume()).
- */
- return perf_mmap__read_forward(md);
-}
-
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
-{
- return perf_evlist__mmap_read_forward(evlist, idx);
-}
-
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
-{
- perf_mmap__consume(&evlist->mmap[idx], false);
-}
-
static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
{
int i;
@@ -761,7 +738,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
map[i].fd = -1;
/*
* When the perf_mmap() call is made we grab one refcount, plus
- * one extra to let perf_evlist__mmap_consume() get the last
+ * one extra to let perf_mmap__consume() get the last
* events after all real references (perf_mmap__get()) are
* dropped.
*
@@ -1086,11 +1063,30 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
+ bool all_threads = (target->per_thread && target->system_wide);
struct cpu_map *cpus;
struct thread_map *threads;
+ /*
+ * If specify '-a' and '--per-thread' to perf record, perf record
+ * will override '--per-thread'. target->per_thread = false and
+ * target->system_wide = true.
+ *
+ * If specify '--per-thread' only to perf record,
+ * target->per_thread = true and target->system_wide = false.
+ *
+ * So target->per_thread && target->system_wide is false.
+ * For perf record, thread_map__new_str doesn't call
+ * thread_map__new_all_cpus. That will keep perf record's
+ * current behavior.
+ *
+ * For perf stat, it allows the case that target->per_thread and
+ * target->system_wide are all true. It means to collect system-wide
+ * per-thread data. thread_map__new_str will call
+ * thread_map__new_all_cpus to enumerate all threads.
+ */
threads = thread_map__new_str(target->pid, target->tid, target->uid,
- target->per_thread);
+ all_threads);
if (!threads)
return -1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 336b838e6957..6c41b2f78713 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -129,10 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
-
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
- int idx);
void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
int perf_evlist__open(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef351688b797..b56e1c2ddaee 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1915,6 +1915,9 @@ try_fallback:
goto fallback_missing_features;
}
out_close:
+ if (err)
+ threads->err_thread = thread;
+
do {
while (--thread >= 0) {
close(FD(evsel, cpu, thread));
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index f28aaaa3a440..942bdec6d70d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -174,4 +174,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
int get_cpuid(char *buffer, size_t sz);
char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
+int strcmp_cpuid_str(const char *s1, const char *s2);
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b6140950301e..44a8456cea10 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -879,7 +879,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
* cumulated only one time to prevent entries more than 100%
* overhead.
*/
- he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
+ he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1));
if (he_cache == NULL)
return -ENOMEM;
@@ -1045,8 +1045,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
if (err)
return err;
- iter->max_stack = max_stack_depth;
-
err = iter->ops->prepare_entry(iter, al);
if (err)
goto out;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 02721b579746..e869cad4d89f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -107,7 +107,6 @@ struct hist_entry_iter {
int curr;
bool hide_unresolved;
- int max_stack;
struct perf_evsel *evsel;
struct perf_sample *sample;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b05a67464c03..12b7427444a3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -48,8 +48,31 @@ static void machine__threads_init(struct machine *machine)
}
}
+static int machine__set_mmap_name(struct machine *machine)
+{
+ if (machine__is_host(machine)) {
+ if (symbol_conf.vmlinux_name)
+ machine->mmap_name = strdup(symbol_conf.vmlinux_name);
+ else
+ machine->mmap_name = strdup("[kernel.kallsyms]");
+ } else if (machine__is_default_guest(machine)) {
+ if (symbol_conf.default_guest_vmlinux_name)
+ machine->mmap_name = strdup(symbol_conf.default_guest_vmlinux_name);
+ else
+ machine->mmap_name = strdup("[guest.kernel.kallsyms]");
+ } else {
+ if (asprintf(&machine->mmap_name, "[guest.kernel.kallsyms.%d]",
+ machine->pid) < 0)
+ machine->mmap_name = NULL;
+ }
+
+ return machine->mmap_name ? 0 : -ENOMEM;
+}
+
int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
{
+ int err = -ENOMEM;
+
memset(machine, 0, sizeof(*machine));
map_groups__init(&machine->kmaps, machine);
RB_CLEAR_NODE(&machine->rb_node);
@@ -73,13 +96,16 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
if (machine->root_dir == NULL)
return -ENOMEM;
+ if (machine__set_mmap_name(machine))
+ goto out;
+
if (pid != HOST_KERNEL_ID) {
struct thread *thread = machine__findnew_thread(machine, -1,
pid);
char comm[64];
if (thread == NULL)
- return -ENOMEM;
+ goto out;
snprintf(comm, sizeof(comm), "[guest/%d]", pid);
thread__set_comm(thread, comm, 0);
@@ -87,7 +113,13 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
}
machine->current_tid = NULL;
+ err = 0;
+out:
+ if (err) {
+ zfree(&machine->root_dir);
+ zfree(&machine->mmap_name);
+ }
return 0;
}
@@ -119,7 +151,7 @@ struct machine *machine__new_kallsyms(void)
* ask for not using the kcore parsing code, once this one is fixed
* to create a map per module.
*/
- if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+ if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
machine__delete(machine);
machine = NULL;
}
@@ -180,6 +212,7 @@ void machine__exit(struct machine *machine)
dsos__exit(&machine->dsos);
machine__exit_vdso(machine);
zfree(&machine->root_dir);
+ zfree(&machine->mmap_name);
zfree(&machine->current_tid);
for (i = 0; i < THREADS__TABLE_SIZE; i++) {
@@ -322,20 +355,6 @@ void machines__process_guests(struct machines *machines,
}
}
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size)
-{
- if (machine__is_host(machine))
- snprintf(bf, size, "[%s]", "kernel.kallsyms");
- else if (machine__is_default_guest(machine))
- snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
- else {
- snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms",
- machine->pid);
- }
-
- return bf;
-}
-
void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
{
struct rb_node *node;
@@ -771,25 +790,13 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
static struct dso *machine__get_kernel(struct machine *machine)
{
- const char *vmlinux_name = NULL;
+ const char *vmlinux_name = machine->mmap_name;
struct dso *kernel;
if (machine__is_host(machine)) {
- vmlinux_name = symbol_conf.vmlinux_name;
- if (!vmlinux_name)
- vmlinux_name = DSO__NAME_KALLSYMS;
-
kernel = machine__findnew_kernel(machine, vmlinux_name,
"[kernel]", DSO_TYPE_KERNEL);
} else {
- char bf[PATH_MAX];
-
- if (machine__is_default_guest(machine))
- vmlinux_name = symbol_conf.default_guest_vmlinux_name;
- if (!vmlinux_name)
- vmlinux_name = machine__mmap_name(machine, bf,
- sizeof(bf));
-
kernel = machine__findnew_kernel(machine, vmlinux_name,
"[guest.kernel]",
DSO_TYPE_GUEST_KERNEL);
@@ -849,13 +856,10 @@ static int machine__get_running_kernel_start(struct machine *machine,
return 0;
}
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+static int
+__machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
int type;
- u64 start = 0;
-
- if (machine__get_running_kernel_start(machine, NULL, &start))
- return -1;
/* In case of renewal the kernel map, destroy previous one */
machine__destroy_kernel_maps(machine);
@@ -864,7 +868,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
struct kmap *kmap;
struct map *map;
- machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+ machine->vmlinux_maps[type] = map__new2(0, kernel, type);
if (machine->vmlinux_maps[type] == NULL)
return -1;
@@ -987,11 +991,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
return machine__create_kernel_maps(machine);
}
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type, bool no_kcore)
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+ enum map_type type)
{
struct map *map = machine__kernel_map(machine);
- int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore);
+ int ret = __dso__load_kallsyms(map->dso, filename, map, true);
if (ret > 0) {
dso__set_loaded(map->dso, type);
@@ -1006,12 +1010,6 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename,
return ret;
}
-int machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type)
-{
- return __machine__load_kallsyms(machine, filename, type, false);
-}
-
int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
{
struct map *map = machine__kernel_map(machine);
@@ -1215,6 +1213,24 @@ static int machine__create_modules(struct machine *machine)
return 0;
}
+static void machine__set_kernel_mmap(struct machine *machine,
+ u64 start, u64 end)
+{
+ int i;
+
+ for (i = 0; i < MAP__NR_TYPES; i++) {
+ machine->vmlinux_maps[i]->start = start;
+ machine->vmlinux_maps[i]->end = end;
+
+ /*
+ * Be a bit paranoid here, some perf.data file came with
+ * a zero sized synthesized MMAP event for the kernel.
+ */
+ if (start == 0 && end == 0)
+ machine->vmlinux_maps[i]->end = ~0ULL;
+ }
+}
+
int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
@@ -1239,40 +1255,22 @@ int machine__create_kernel_maps(struct machine *machine)
"continuing anyway...\n", machine->pid);
}
- /*
- * Now that we have all the maps created, just set the ->end of them:
- */
- map_groups__fixup_end(&machine->kmaps);
-
if (!machine__get_running_kernel_start(machine, &name, &addr)) {
if (name &&
maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
machine__destroy_kernel_maps(machine);
return -1;
}
+ machine__set_kernel_mmap(machine, addr, 0);
}
+ /*
+ * Now that we have all the maps created, just set the ->end of them:
+ */
+ map_groups__fixup_end(&machine->kmaps);
return 0;
}
-static void machine__set_kernel_mmap_len(struct machine *machine,
- union perf_event *event)
-{
- int i;
-
- for (i = 0; i < MAP__NR_TYPES; i++) {
- machine->vmlinux_maps[i]->start = event->mmap.start;
- machine->vmlinux_maps[i]->end = (event->mmap.start +
- event->mmap.len);
- /*
- * Be a bit paranoid here, some perf.data file came with
- * a zero sized synthesized MMAP event for the kernel.
- */
- if (machine->vmlinux_maps[i]->end == 0)
- machine->vmlinux_maps[i]->end = ~0ULL;
- }
-}
-
static bool machine__uses_kcore(struct machine *machine)
{
struct dso *dso;
@@ -1289,7 +1287,6 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
union perf_event *event)
{
struct map *map;
- char kmmap_prefix[PATH_MAX];
enum dso_kernel_type kernel_type;
bool is_kernel_mmap;
@@ -1297,15 +1294,14 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
if (machine__uses_kcore(machine))
return 0;
- machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
if (machine__is_host(machine))
kernel_type = DSO_TYPE_KERNEL;
else
kernel_type = DSO_TYPE_GUEST_KERNEL;
is_kernel_mmap = memcmp(event->mmap.filename,
- kmmap_prefix,
- strlen(kmmap_prefix) - 1) == 0;
+ machine->mmap_name,
+ strlen(machine->mmap_name) - 1) == 0;
if (event->mmap.filename[0] == '/' ||
(!is_kernel_mmap && event->mmap.filename[0] == '[')) {
map = machine__findnew_module_map(machine, event->mmap.start,
@@ -1316,7 +1312,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
map->end = map->start + event->mmap.len;
} else if (is_kernel_mmap) {
const char *symbol_name = (event->mmap.filename +
- strlen(kmmap_prefix));
+ strlen(machine->mmap_name));
/*
* Should be there already, from the build-id table in
* the header.
@@ -1357,7 +1353,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
up_read(&machine->dsos.lock);
if (kernel == NULL)
- kernel = machine__findnew_dso(machine, kmmap_prefix);
+ kernel = machine__findnew_dso(machine, machine->mmap_name);
if (kernel == NULL)
goto out_problem;
@@ -1370,7 +1366,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
if (strstr(kernel->long_name, "vmlinux"))
dso__set_short_name(kernel, "[kernel.vmlinux]", false);
- machine__set_kernel_mmap_len(machine, event);
+ machine__set_kernel_mmap(machine, event->mmap.start,
+ event->mmap.start + event->mmap.len);
/*
* Avoid using a zero address (kptr_restrict) for the ref reloc
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5ce860b64c74..66cc200ef86f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -43,6 +43,7 @@ struct machine {
bool comm_exec;
bool kptr_restrict_warned;
char *root_dir;
+ char *mmap_name;
struct threads threads[THREADS__TABLE_SIZE];
struct vdso_info *vdso_info;
struct perf_env *env;
@@ -142,8 +143,6 @@ struct machine *machines__find(struct machines *machines, pid_t pid);
struct machine *machines__findnew(struct machines *machines, pid_t pid);
void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
-
void machines__set_comm_exec(struct machines *machines, bool comm_exec);
struct machine *machine__new_host(void);
@@ -226,8 +225,6 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
int arch__fix_module_text_start(u64 *start, const char *name);
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type, bool no_kcore);
int machine__load_kallsyms(struct machine *machine, const char *filename,
enum map_type type);
int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
@@ -239,7 +236,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm);
void machine__destroy_kernel_maps(struct machine *machine);
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
int machine__create_kernel_maps(struct machine *machine);
int machines__create_kernel_maps(struct machines *machines, pid_t pid);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 91531a7c8fbf..4f27c464ce0b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -64,25 +64,6 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
}
/*
- * legacy interface for mmap read.
- * Don't use it. Use perf_mmap__read_event().
- */
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
-{
- u64 head;
-
- /*
- * Check if event was unmapped due to a POLLHUP/POLLERR.
- */
- if (!refcount_read(&map->refcnt))
- return NULL;
-
- head = perf_mmap__read_head(map);
-
- return perf_mmap__read(map, &map->prev, head);
-}
-
-/*
* Read event from ring buffer one by one.
* Return one event for each call.
*
@@ -191,7 +172,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
{
/*
- * The last one will be done at perf_evlist__mmap_consume(), so that we
+ * The last one will be done at perf_mmap__consume(), so that we
* make sure we don't prevent tools from consuming every last event in
* the ring buffer.
*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 57e38fdf0b34..1111d5bf15ca 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -576,6 +576,34 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
return NULL;
}
+/* Return zero when the cpuid from the mapfile.csv matches the
+ * cpuid string generated on this platform.
+ * Otherwise return non-zero.
+ */
+int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+ regex_t re;
+ regmatch_t pmatch[1];
+ int match;
+
+ if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+ /* Warn unable to generate match particular string. */
+ pr_info("Invalid regular expression %s\n", mapcpuid);
+ return 1;
+ }
+
+ match = !regexec(&re, cpuid, 1, pmatch, 0);
+ regfree(&re);
+ if (match) {
+ size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+ /* Verify the entire string matched. */
+ if (match_len == strlen(cpuid))
+ return 0;
+ }
+ return 1;
+}
+
static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
{
char *cpuid;
@@ -610,31 +638,14 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
i = 0;
for (;;) {
- regex_t re;
- regmatch_t pmatch[1];
- int match;
-
map = &pmu_events_map[i++];
if (!map->table) {
map = NULL;
break;
}
- if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
- /* Warn unable to generate match particular string. */
- pr_info("Invalid regular expression %s\n", map->cpuid);
+ if (!strcmp_cpuid_str(map->cpuid, cpuid))
break;
- }
-
- match = !regexec(&re, cpuid, 1, pmatch, 0);
- regfree(&re);
- if (match) {
- size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
-
- /* Verify the entire string matched. */
- if (match_len == strlen(cpuid))
- break;
- }
}
free(cpuid);
return map;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index b1e999bd21ef..35fb5ef7d290 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -12,6 +12,30 @@
#include "print_binary.h"
#include "thread_map.h"
+#if PY_MAJOR_VERSION < 3
+#define _PyUnicode_FromString(arg) \
+ PyString_FromString(arg)
+#define _PyUnicode_AsString(arg) \
+ PyString_AsString(arg)
+#define _PyUnicode_FromFormat(...) \
+ PyString_FromFormat(__VA_ARGS__)
+#define _PyLong_FromLong(arg) \
+ PyInt_FromLong(arg)
+
+#else
+
+#define _PyUnicode_FromString(arg) \
+ PyUnicode_FromString(arg)
+#define _PyUnicode_FromFormat(...) \
+ PyUnicode_FromFormat(__VA_ARGS__)
+#define _PyLong_FromLong(arg) \
+ PyLong_FromLong(arg)
+#endif
+
+#ifndef Py_TYPE
+#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
+#endif
+
/*
* Provide these two so that we don't have to link against callchain.c and
* start dragging hist.c, etc.
@@ -49,7 +73,11 @@ int eprintf(int level, int var, const char *fmt, ...)
# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
#endif
+#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initperf(void);
+#else
+PyMODINIT_FUNC PyInit_perf(void);
+#endif
#define member_def(type, member, ptype, help) \
{ #member, ptype, \
@@ -107,7 +135,7 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
ret = PyErr_NoMemory();
} else {
- ret = PyString_FromString(s);
+ ret = _PyUnicode_FromString(s);
free(s);
}
return ret;
@@ -138,7 +166,7 @@ static PyMemberDef pyrf_task_event__members[] = {
static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
{
- return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+ return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
"ptid: %u, time: %" PRIu64 "}",
pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
pevent->event.fork.pid,
@@ -171,7 +199,7 @@ static PyMemberDef pyrf_comm_event__members[] = {
static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
{
- return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+ return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
pevent->event.comm.pid,
pevent->event.comm.tid,
pevent->event.comm.comm);
@@ -202,7 +230,7 @@ static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
{
struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
- return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+ return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
", stream_id: %" PRIu64 " }",
pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
te->time, te->id, te->stream_id);
@@ -237,7 +265,7 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
pevent->event.lost.id, pevent->event.lost.lost) < 0) {
ret = PyErr_NoMemory();
} else {
- ret = PyString_FromString(s);
+ ret = _PyUnicode_FromString(s);
free(s);
}
return ret;
@@ -264,7 +292,7 @@ static PyMemberDef pyrf_read_event__members[] = {
static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent)
{
- return PyString_FromFormat("{ type: read, pid: %u, tid: %u }",
+ return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }",
pevent->event.read.pid,
pevent->event.read.tid);
/*
@@ -299,7 +327,7 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
if (asprintf(&s, "{ type: sample }") < 0) {
ret = PyErr_NoMemory();
} else {
- ret = PyString_FromString(s);
+ ret = _PyUnicode_FromString(s);
free(s);
}
return ret;
@@ -330,7 +358,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
}
if (field->flags & FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
- ret = PyString_FromString((char *)data + offset);
+ ret = _PyUnicode_FromString((char *)data + offset);
} else {
ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
field->flags &= ~FIELD_IS_STRING;
@@ -352,7 +380,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
static PyObject*
get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
{
- const char *str = PyString_AsString(PyObject_Str(attr_name));
+ const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
struct perf_evsel *evsel = pevent->evsel;
struct format_field *field;
@@ -416,7 +444,7 @@ static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent)
!!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) {
ret = PyErr_NoMemory();
} else {
- ret = PyString_FromString(s);
+ ret = _PyUnicode_FromString(s);
free(s);
}
return ret;
@@ -528,7 +556,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
{
cpu_map__put(pcpus->cpus);
- pcpus->ob_type->tp_free((PyObject*)pcpus);
+ Py_TYPE(pcpus)->tp_free((PyObject*)pcpus);
}
static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
@@ -597,7 +625,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
{
thread_map__put(pthreads->threads);
- pthreads->ob_type->tp_free((PyObject*)pthreads);
+ Py_TYPE(pthreads)->tp_free((PyObject*)pthreads);
}
static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
@@ -759,7 +787,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
{
perf_evsel__exit(&pevsel->evsel);
- pevsel->ob_type->tp_free((PyObject*)pevsel);
+ Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
}
static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
@@ -850,7 +878,7 @@ static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
{
perf_evlist__exit(&pevlist->evlist);
- pevlist->ob_type->tp_free((PyObject*)pevlist);
+ Py_TYPE(pevlist)->tp_free((PyObject*)pevlist);
}
static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
@@ -902,12 +930,16 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
for (i = 0; i < evlist->pollfd.nr; ++i) {
PyObject *file;
+#if PY_MAJOR_VERSION < 3
FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
if (fp == NULL)
goto free_list;
file = PyFile_FromFile(fp, "perf", "r", NULL);
+#else
+ file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1);
+#endif
if (file == NULL)
goto free_list;
@@ -951,13 +983,19 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
union perf_event *event;
int sample_id_all = 1, cpu;
static char *kwlist[] = { "cpu", "sample_id_all", NULL };
+ struct perf_mmap *md;
+ u64 end, start;
int err;
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
&cpu, &sample_id_all))
return NULL;
- event = perf_evlist__mmap_read(evlist, cpu);
+ md = &evlist->mmap[cpu];
+ if (perf_mmap__read_init(md, false, &start, &end) < 0)
+ goto end;
+
+ event = perf_mmap__read_event(md, false, &start, end);
if (event != NULL) {
PyObject *pyevent = pyrf_event__new(event);
struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
@@ -975,14 +1013,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
/* Consume the even only after we parsed it out. */
- perf_evlist__mmap_consume(evlist, cpu);
+ perf_mmap__consume(md, false);
if (err)
return PyErr_Format(PyExc_OSError,
"perf: can't parse sample, err=%d", err);
return pyevent;
}
-
+end:
Py_INCREF(Py_None);
return Py_None;
}
@@ -1194,9 +1232,9 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
tp_format = trace_event__tp_format(sys, name);
if (IS_ERR(tp_format))
- return PyInt_FromLong(-1);
+ return _PyLong_FromLong(-1);
- return PyInt_FromLong(tp_format->id);
+ return _PyLong_FromLong(tp_format->id);
}
static PyMethodDef perf__methods[] = {
@@ -1209,11 +1247,31 @@ static PyMethodDef perf__methods[] = {
{ .ml_name = NULL, }
};
+#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initperf(void)
+#else
+PyMODINIT_FUNC PyInit_perf(void)
+#endif
{
PyObject *obj;
int i;
- PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+ PyObject *dict;
+#if PY_MAJOR_VERSION < 3
+ PyObject *module = Py_InitModule("perf", perf__methods);
+#else
+ static struct PyModuleDef moduledef = {
+ PyModuleDef_HEAD_INIT,
+ "perf", /* m_name */
+ "", /* m_doc */
+ -1, /* m_size */
+ perf__methods, /* m_methods */
+ NULL, /* m_reload */
+ NULL, /* m_traverse */
+ NULL, /* m_clear */
+ NULL, /* m_free */
+ };
+ PyObject *module = PyModule_Create(&moduledef);
+#endif
if (module == NULL ||
pyrf_event__setup_types() < 0 ||
@@ -1221,7 +1279,11 @@ PyMODINIT_FUNC initperf(void)
pyrf_evsel__setup_types() < 0 ||
pyrf_thread_map__setup_types() < 0 ||
pyrf_cpu_map__setup_types() < 0)
+#if PY_MAJOR_VERSION < 3
return;
+#else
+ return module;
+#endif
/* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
@@ -1270,7 +1332,7 @@ PyMODINIT_FUNC initperf(void)
goto error;
for (i = 0; perf__constants[i].name != NULL; i++) {
- obj = PyInt_FromLong(perf__constants[i].value);
+ obj = _PyLong_FromLong(perf__constants[i].value);
if (obj == NULL)
goto error;
PyDict_SetItemString(dict, perf__constants[i].name, obj);
@@ -1280,6 +1342,9 @@ PyMODINIT_FUNC initperf(void)
error:
if (PyErr_Occurred())
PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+#if PY_MAJOR_VERSION >= 3
+ return module;
+#endif
}
/*
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 6f09e4962dad..9cfc7bf16531 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -5,6 +5,7 @@
#include "parse-events.h"
#include <errno.h>
#include <api/fs/fs.h>
+#include <subcmd/parse-options.h>
#include "util.h"
#include "cloexec.h"
@@ -219,11 +220,21 @@ static int record_opts__config_freq(struct record_opts *opts)
* User specified frequency is over current maximum.
*/
if (user_freq && (max_rate < opts->freq)) {
- pr_err("Maximum frequency rate (%u) reached.\n"
- "Please use -F freq option with lower value or consider\n"
- "tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
- max_rate);
- return -1;
+ if (opts->strict_freq) {
+ pr_err("error: Maximum frequency rate (%'u Hz) exceeded.\n"
+ " Please use -F freq option with a lower value or consider\n"
+ " tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
+ max_rate);
+ return -1;
+ } else {
+ pr_warning("warning: Maximum frequency rate (%'u Hz) exceeded, throttling from %'u Hz to %'u Hz.\n"
+ " The limit can be raised via /proc/sys/kernel/perf_event_max_sample_rate.\n"
+ " The kernel will lower it when perf's interrupts take too long.\n"
+ " Use --strict-freq to disable this throttling, refusing to record.\n",
+ max_rate, opts->freq, max_rate);
+
+ opts->freq = max_rate;
+ }
}
/*
@@ -291,3 +302,25 @@ out_delete:
perf_evlist__delete(temp_evlist);
return ret;
}
+
+int record__parse_freq(const struct option *opt, const char *str, int unset __maybe_unused)
+{
+ unsigned int freq;
+ struct record_opts *opts = opt->value;
+
+ if (!str)
+ return -EINVAL;
+
+ if (strcasecmp(str, "max") == 0) {
+ if (get_max_rate(&freq)) {
+ pr_err("couldn't read /proc/sys/kernel/perf_event_max_sample_rate\n");
+ return -1;
+ }
+ pr_info("info: Using a maximum frequency rate of %'d Hz\n", freq);
+ } else {
+ freq = atoi(str);
+ }
+
+ opts->user_freq = freq;
+ return 0;
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ea070883c593..10dd5fce082b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -49,7 +49,37 @@
#include "print_binary.h"
#include "stat.h"
+#if PY_MAJOR_VERSION < 3
+#define _PyUnicode_FromString(arg) \
+ PyString_FromString(arg)
+#define _PyUnicode_FromStringAndSize(arg1, arg2) \
+ PyString_FromStringAndSize((arg1), (arg2))
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+ PyString_FromStringAndSize((arg1), (arg2))
+#define _PyLong_FromLong(arg) \
+ PyInt_FromLong(arg)
+#define _PyLong_AsLong(arg) \
+ PyInt_AsLong(arg)
+#define _PyCapsule_New(arg1, arg2, arg3) \
+ PyCObject_FromVoidPtr((arg1), (arg2))
+
PyMODINIT_FUNC initperf_trace_context(void);
+#else
+#define _PyUnicode_FromString(arg) \
+ PyUnicode_FromString(arg)
+#define _PyUnicode_FromStringAndSize(arg1, arg2) \
+ PyUnicode_FromStringAndSize((arg1), (arg2))
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+ PyBytes_FromStringAndSize((arg1), (arg2))
+#define _PyLong_FromLong(arg) \
+ PyLong_FromLong(arg)
+#define _PyLong_AsLong(arg) \
+ PyLong_AsLong(arg)
+#define _PyCapsule_New(arg1, arg2, arg3) \
+ PyCapsule_New((arg1), (arg2), (arg3))
+
+PyMODINIT_FUNC PyInit_perf_trace_context(void);
+#endif
#define TRACE_EVENT_TYPE_MAX \
((1 << (sizeof(unsigned short) * 8)) - 1)
@@ -135,7 +165,7 @@ static int get_argument_count(PyObject *handler)
PyObject *arg_count_obj = PyObject_GetAttrString(code_obj,
"co_argcount");
if (arg_count_obj) {
- arg_count = (int) PyInt_AsLong(arg_count_obj);
+ arg_count = (int) _PyLong_AsLong(arg_count_obj);
Py_DECREF(arg_count_obj);
}
Py_DECREF(code_obj);
@@ -182,10 +212,10 @@ static void define_value(enum print_arg_type field_type,
value = eval_flag(field_value);
- PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
- PyTuple_SetItem(t, n++, PyString_FromString(field_name));
- PyTuple_SetItem(t, n++, PyInt_FromLong(value));
- PyTuple_SetItem(t, n++, PyString_FromString(field_str));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(value));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_str));
try_call_object(handler_name, t);
@@ -223,10 +253,10 @@ static void define_field(enum print_arg_type field_type,
if (!t)
Py_FatalError("couldn't create Python tuple");
- PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
- PyTuple_SetItem(t, n++, PyString_FromString(field_name));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
if (field_type == PRINT_FLAGS)
- PyTuple_SetItem(t, n++, PyString_FromString(delim));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
try_call_object(handler_name, t);
@@ -325,12 +355,12 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
if (field->flags & FIELD_IS_SIGNED) {
if ((long long)val >= LONG_MIN &&
(long long)val <= LONG_MAX)
- obj = PyInt_FromLong(val);
+ obj = _PyLong_FromLong(val);
else
obj = PyLong_FromLongLong(val);
} else {
if (val <= LONG_MAX)
- obj = PyInt_FromLong(val);
+ obj = _PyLong_FromLong(val);
else
obj = PyLong_FromUnsignedLongLong(val);
}
@@ -389,9 +419,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
pydict_set_item_string_decref(pysym, "end",
PyLong_FromUnsignedLongLong(node->sym->end));
pydict_set_item_string_decref(pysym, "binding",
- PyInt_FromLong(node->sym->binding));
+ _PyLong_FromLong(node->sym->binding));
pydict_set_item_string_decref(pysym, "name",
- PyString_FromStringAndSize(node->sym->name,
+ _PyUnicode_FromStringAndSize(node->sym->name,
node->sym->namelen));
pydict_set_item_string_decref(pyelem, "sym", pysym);
}
@@ -406,7 +436,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
dsoname = map->dso->name;
}
pydict_set_item_string_decref(pyelem, "dso",
- PyString_FromString(dsoname));
+ _PyUnicode_FromString(dsoname));
}
callchain_cursor_advance(&callchain_cursor);
@@ -483,16 +513,16 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
if (!dict_sample)
Py_FatalError("couldn't create Python dictionary");
- pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
- pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
+ pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
+ pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize(
(const char *)&evsel->attr, sizeof(evsel->attr)));
pydict_set_item_string_decref(dict_sample, "pid",
- PyInt_FromLong(sample->pid));
+ _PyLong_FromLong(sample->pid));
pydict_set_item_string_decref(dict_sample, "tid",
- PyInt_FromLong(sample->tid));
+ _PyLong_FromLong(sample->tid));
pydict_set_item_string_decref(dict_sample, "cpu",
- PyInt_FromLong(sample->cpu));
+ _PyLong_FromLong(sample->cpu));
pydict_set_item_string_decref(dict_sample, "ip",
PyLong_FromUnsignedLongLong(sample->ip));
pydict_set_item_string_decref(dict_sample, "time",
@@ -504,17 +534,17 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
set_sample_read_in_dict(dict_sample, sample, evsel);
pydict_set_item_string_decref(dict, "sample", dict_sample);
- pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
+ pydict_set_item_string_decref(dict, "raw_buf", _PyBytes_FromStringAndSize(
(const char *)sample->raw_data, sample->raw_size));
pydict_set_item_string_decref(dict, "comm",
- PyString_FromString(thread__comm_str(al->thread)));
+ _PyUnicode_FromString(thread__comm_str(al->thread)));
if (al->map) {
pydict_set_item_string_decref(dict, "dso",
- PyString_FromString(al->map->dso->name));
+ _PyUnicode_FromString(al->map->dso->name));
}
if (al->sym) {
pydict_set_item_string_decref(dict, "symbol",
- PyString_FromString(al->sym->name));
+ _PyUnicode_FromString(al->sym->name));
}
pydict_set_item_string_decref(dict, "callchain", callchain);
@@ -574,9 +604,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
scripting_context->event_data = data;
scripting_context->pevent = evsel->tp_format->pevent;
- context = PyCObject_FromVoidPtr(scripting_context, NULL);
+ context = _PyCapsule_New(scripting_context, NULL, NULL);
- PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(handler_name));
PyTuple_SetItem(t, n++, context);
/* ip unwinding */
@@ -585,18 +615,18 @@ static void python_process_tracepoint(struct perf_sample *sample,
Py_INCREF(callchain);
if (!dict) {
- PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
- PyTuple_SetItem(t, n++, PyInt_FromLong(s));
- PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
- PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
- PyTuple_SetItem(t, n++, PyString_FromString(comm));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(s));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(ns));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(pid));
+ PyTuple_SetItem(t, n++, _PyUnicode_FromString(comm));
PyTuple_SetItem(t, n++, callchain);
} else {
- pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
- pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
- pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
- pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
- pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+ pydict_set_item_string_decref(dict, "common_cpu", _PyLong_FromLong(cpu));
+ pydict_set_item_string_decref(dict, "common_s", _PyLong_FromLong(s));
+ pydict_set_item_string_decref(dict, "common_ns", _PyLong_FromLong(ns));
+ pydict_set_item_string_decref(dict, "common_pid", _PyLong_FromLong(pid));
+ pydict_set_item_string_decref(dict, "common_comm", _PyUnicode_FromString(comm));
pydict_set_item_string_decref(dict, "common_callchain", callchain);
}
for (field = event->format.fields; field; field = field->next) {
@@ -615,7 +645,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
}
if (field->flags & FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
- obj = PyString_FromString((char *) data + offset);
+ obj = _PyUnicode_FromString((char *) data + offset);
} else {
obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
field->flags &= ~FIELD_IS_STRING;
@@ -668,7 +698,7 @@ static PyObject *tuple_new(unsigned int sz)
static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
{
#if BITS_PER_LONG == 64
- return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+ return PyTuple_SetItem(t, pos, _PyLong_FromLong(val));
#endif
#if BITS_PER_LONG == 32
return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
@@ -677,12 +707,12 @@ static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
{
- return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+ return PyTuple_SetItem(t, pos, _PyLong_FromLong(val));
}
static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
{
- return PyTuple_SetItem(t, pos, PyString_FromString(s));
+ return PyTuple_SetItem(t, pos, _PyUnicode_FromString(s));
}
static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
@@ -1029,8 +1059,8 @@ process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
return;
}
- PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
- PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+ PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
tuple_set_u64(t, n++, tstamp);
tuple_set_u64(t, n++, count->val);
@@ -1212,27 +1242,58 @@ static void set_table_handlers(struct tables *tables)
SET_TABLE_HANDLER(call_return);
}
+#if PY_MAJOR_VERSION < 3
+static void _free_command_line(const char **command_line, int num)
+{
+ free(command_line);
+}
+#else
+static void _free_command_line(wchar_t **command_line, int num)
+{
+ int i;
+ for (i = 0; i < num; i++)
+ PyMem_RawFree(command_line[i]);
+ free(command_line);
+}
+#endif
+
+
/*
* Start trace script
*/
static int python_start_script(const char *script, int argc, const char **argv)
{
struct tables *tables = &tables_global;
+#if PY_MAJOR_VERSION < 3
const char **command_line;
+#else
+ wchar_t **command_line;
+#endif
char buf[PATH_MAX];
int i, err = 0;
FILE *fp;
+#if PY_MAJOR_VERSION < 3
command_line = malloc((argc + 1) * sizeof(const char *));
command_line[0] = script;
for (i = 1; i < argc + 1; i++)
command_line[i] = argv[i - 1];
+#else
+ command_line = malloc((argc + 1) * sizeof(wchar_t *));
+ command_line[0] = Py_DecodeLocale(script, NULL);
+ for (i = 1; i < argc + 1; i++)
+ command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+#endif
Py_Initialize();
+#if PY_MAJOR_VERSION < 3
initperf_trace_context();
-
PySys_SetArgv(argc + 1, (char **)command_line);
+#else
+ PyInit_perf_trace_context();
+ PySys_SetArgv(argc + 1, command_line);
+#endif
fp = fopen(script, "r");
if (!fp) {
@@ -1262,12 +1323,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
goto error;
}
- free(command_line);
+ _free_command_line(command_line, argc + 1);
return err;
error:
Py_Finalize();
- free(command_line);
+ _free_command_line(command_line, argc + 1);
return err;
}
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index af415febbc46..6891635b50c3 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python2
+#!/usr/bin/python
from os import getenv
@@ -35,11 +35,11 @@ build_tmp = getenv('PYTHON_EXTBUILD_TMP')
libtraceevent = getenv('LIBTRACEEVENT')
libapikfs = getenv('LIBAPI')
-ext_sources = [f.strip() for f in file('util/python-ext-sources')
+ext_sources = [f.strip() for f in open('util/python-ext-sources')
if len(f.strip()) > 0 and f[0] != '#']
# use full paths with source files
-ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
perf = Extension('perf',
sources = ext_sources,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2da4d0456a03..e8514f651865 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -111,17 +111,20 @@ struct sort_entry sort_thread = {
/* --sort comm */
+/*
+ * We can't use pointer comparison in functions below,
+ * because it gives different results based on pointer
+ * values, which could break some sorting assumptions.
+ */
static int64_t
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
- /* Compare the addr that should be unique among comm */
return strcmp(comm__str(right->comm), comm__str(left->comm));
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
- /* Compare the addr that should be unique among comm */
return strcmp(comm__str(right->comm), comm__str(left->comm));
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index dbc6f7134f61..2f44e386a0e8 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,6 +90,8 @@ struct perf_stat_config {
bool scale;
FILE *output;
unsigned int interval;
+ unsigned int timeout;
+ int times;
struct runtime_stat *stats;
int stats_num;
};
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cc065d4bfafc..a1a312d99f30 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1582,7 +1582,7 @@ int dso__load(struct dso *dso, struct map *map)
bool next_slot = false;
bool is_reg;
bool nsexit;
- int sirc;
+ int sirc = -1;
enum dso_binary_type symtab_type = binary_type_symtab[i];
@@ -1600,16 +1600,14 @@ int dso__load(struct dso *dso, struct map *map)
nsinfo__mountns_exit(&nsc);
is_reg = is_regular_file(name);
- sirc = symsrc__init(ss, dso, name, symtab_type);
+ if (is_reg)
+ sirc = symsrc__init(ss, dso, name, symtab_type);
if (nsexit)
nsinfo__mountns_enter(dso->nsinfo, &nsc);
- if (!is_reg || sirc < 0) {
- if (sirc >= 0)
- symsrc__destroy(ss);
+ if (!is_reg || sirc < 0)
continue;
- }
if (!syms_ss && symsrc__has_symtab(ss)) {
syms_ss = ss;
@@ -1960,8 +1958,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
pr_debug("Using %s for symbols\n", kallsyms_filename);
if (err > 0 && !dso__is_kcore(dso)) {
dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
- machine__mmap_name(machine, path, sizeof(path));
- dso__set_long_name(dso, strdup(path), true);
+ dso__set_long_name(dso, machine->mmap_name, false);
map__fixup_start(map);
map__fixup_end(map);
}
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 303bdb84ab5a..895122d638dd 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -30,6 +30,14 @@ static const char **syscalltbl_native = syscalltbl_x86_64;
#include <asm/syscalls_64.c>
const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID;
static const char **syscalltbl_native = syscalltbl_s390_64;
+#elif defined(__powerpc64__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_64;
+#elif defined(__powerpc__)
+#include <asm/syscalls_32.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_32;
#endif
struct syscall {
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 3e1038f6491c..5d467d8ae9ab 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -32,6 +32,7 @@ static void thread_map__reset(struct thread_map *map, int start, int nr)
size_t size = (nr - start) * sizeof(map->map[0]);
memset(&map->map[start], 0, size);
+ map->err_thread = -1;
}
static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
@@ -323,7 +324,7 @@ out_free_threads:
}
struct thread_map *thread_map__new_str(const char *pid, const char *tid,
- uid_t uid, bool per_thread)
+ uid_t uid, bool all_threads)
{
if (pid)
return thread_map__new_by_pid_str(pid);
@@ -331,7 +332,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
if (!tid && uid != UINT_MAX)
return thread_map__new_by_uid(uid);
- if (per_thread)
+ if (all_threads)
return thread_map__new_all_cpus();
return thread_map__new_by_tid_str(tid);
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0a806b99e73c..2f689c90a8c6 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -14,6 +14,7 @@ struct thread_map_data {
struct thread_map {
refcount_t refcnt;
int nr;
+ int err_thread;
struct thread_map_data map[];
};
@@ -31,7 +32,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
void thread_map__put(struct thread_map *map);
struct thread_map *thread_map__new_str(const char *pid,
- const char *tid, uid_t uid, bool per_thread);
+ const char *tid, uid_t uid, bool all_threads);
struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
Powered by cgit, Gruvboxed by Blaster4385.