struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
return 0;
for (i = 0; i < br->nr; i++) {
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
if (PRINT_FIELD(DSO)) {
memset(&alf, 0, sizeof(alf));
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str( br->entries + i),
- br->entries[i].flags.in_tx? 'X' : '-',
- br->entries[i].flags.abort? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt));
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
thread__find_symbol_fb(thread, sample->cpumode, from, &alf);
thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
printed += fprintf(fp, ")");
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str( br->entries + i),
- br->entries[i].flags.in_tx? 'X' : '-',
- br->entries[i].flags.abort? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
struct perf_event_attr *attr, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt;
u64 i, from, to;
int printed = 0;
memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt));
- from = br->entries[i].from;
- to = br->entries[i].to;
+ from = entries[i].from;
+ to = entries[i].to;
if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&
!alf.map->dso->adjust_symbols)
printed += fprintf(fp, ")");
}
printed += fprintf(fp, "/%c/%c/%c/%d ",
- mispred_str(br->entries + i),
- br->entries[i].flags.in_tx ? 'X' : '-',
- br->entries[i].flags.abort ? 'A' : '-',
- br->entries[i].flags.cycles);
+ mispred_str(entries + i),
+ entries[i].flags.in_tx ? 'X' : '-',
+ entries[i].flags.abort ? 'A' : '-',
+ entries[i].flags.cycles);
}
return printed;
struct machine *machine, FILE *fp)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 start, end;
int i, insn, len, nr, ilen, printed = 0;
struct perf_insn x;
printed += fprintf(fp, "%c", '\n');
/* Handle first from jump, of which we don't know the entry. */
- len = grab_bb(buffer, br->entries[nr-1].from,
- br->entries[nr-1].from,
+ len = grab_bb(buffer, entries[nr-1].from,
+ entries[nr-1].from,
machine, thread, &x.is64bit, &x.cpumode, false);
if (len > 0) {
- printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+ printed += ip__fprintf_sym(entries[nr - 1].from, thread,
x.cpumode, x.cpu, &lastsym, attr, fp);
- printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+ printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
&x, buffer, len, 0, fp, &total_cycles);
if (PRINT_FIELD(SRCCODE))
- printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);
+ printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
}
/* Print all blocks */
for (i = nr - 2; i >= 0; i--) {
- if (br->entries[i].from || br->entries[i].to)
+ if (entries[i].from || entries[i].to)
pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
- br->entries[i].from,
- br->entries[i].to);
- start = br->entries[i + 1].to;
- end = br->entries[i].from;
+ entries[i].from,
+ entries[i].to);
+ start = entries[i + 1].to;
+ end = entries[i].from;
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
/* Patch up missing kernel transfers due to ring filters */
if (len == -ENXIO && i > 0) {
- end = br->entries[--i].from;
+ end = entries[--i].from;
pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
}
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) {
- printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
+ printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
&total_cycles);
if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, ip);
* Hit the branch? In this case we are already done, and the target
* has not been executed yet.
*/
- if (br->entries[0].from == sample->ip)
+ if (entries[0].from == sample->ip)
goto out;
- if (br->entries[0].flags.abort)
+ if (entries[0].flags.abort)
goto out;
/*
* between final branch and sample. When this happens just
* continue walking after the last TO until we hit a branch.
*/
- start = br->entries[0].to;
+ start = entries[0].to;
end = sample->ip;
if (end < start) {
/* Missing jump. Scan 128 bytes for the next branch */
if (type & PERF_SAMPLE_BRANCH_STACK) {
COMP(branch_stack->nr);
+ COMP(branch_stack->hw_idx);
for (i = 0; i < s1->branch_stack->nr; i++)
MCOMP(branch_stack->entries[i]);
}
u64 data[64];
} branch_stack = {
/* 1 branch_entry */
- .data = {1, 211, 212, 213},
+ .data = {1, -1ULL, 211, 212, 213},
};
u64 regs[64];
const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
.transaction = 112,
.raw_data = (void *)raw_data,
.callchain = &callchain.callchain,
+ .no_hw_idx = false,
.branch_stack = &branch_stack.branch_stack,
.user_regs = {
.abi = PERF_SAMPLE_REGS_ABI_64,
if (sample_type & PERF_SAMPLE_REGS_INTR)
evsel.core.attr.sample_regs_intr = sample_regs;
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+ evsel.core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+
for (i = 0; i < sizeof(regs); i++)
*(i + (u8 *)regs) = i & 0xfe;
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <linux/types.h>
+#include "event.h"
struct branch_flags {
u64 mispred:1;
struct branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries[0];
};
+/*
+ * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.
+ * Otherwise, the output format of a sample with branch stack is
+ * struct branch_stack {
+ * u64 nr;
+ * struct branch_entry entries[0];
+ * }
+ * Check whether the hw_idx is available,
+ * and return the corresponding pointer of entries[0].
+ */
+static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)
+{
+ u64 *entry = (u64 *)sample->branch_stack;
+
+ entry++;
+ if (sample->no_hw_idx)
+ return (struct branch_entry *)entry;
+ return (struct branch_entry *)(++entry);
+}
+
struct branch_type_stat {
bool branch_to;
u64 counts[PERF_BR_MAX];
union perf_event *event = tidq->event_buf;
struct dummy_branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries;
} dummy_bs;
u64 ip;
if (etm->synth_opts.last_branch) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
+ .hw_idx = -1ULL,
.entries = {
.from = sample.ip,
.to = sample.addr,
u16 insn_len;
u8 cpumode;
u16 misc;
+ bool no_hw_idx; /* No hw_idx collected in branch_stack */
char insn[MAX_INSN];
void *raw_data;
struct ip_callchain *callchain;
if (data->branch_stack->nr > max_branch_nr)
return -EFAULT;
+
sz = data->branch_stack->nr * sizeof(struct branch_entry);
+ if (perf_evsel__has_branch_hw_idx(evsel))
+ sz += sizeof(u64);
+ else
+ data->no_hw_idx = true;
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
+static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+{
+ return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
static inline bool evsel__has_callchain(const struct evsel *evsel)
{
return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
u64 *total_cycles)
{
struct branch_info *bi;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
/* If we have branch cycles always annotate them. */
- if (bs && bs->nr && bs->entries[0].flags.cycles) {
+ if (bs && bs->nr && entries[0].flags.cycles) {
int i;
bi = sample__resolve_bstack(sample, al);
struct perf_sample sample = { .ip = 0, };
struct dummy_branch_stack {
u64 nr;
+ u64 hw_idx;
struct branch_entry entries;
} dummy_bs;
if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
+ .hw_idx = -1ULL,
.entries = {
.from = sample.ip,
.to = sample.addr,
{
unsigned int i;
const struct branch_stack *bs = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
if (!bi)
return NULL;
for (i = 0; i < bs->nr; i++) {
- ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
- ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
- bi[i].flags = bs->entries[i].flags;
+ ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
+ ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
+ bi[i].flags = entries[i].flags;
}
return bi;
}
/* LBR only affects the user callchain */
if (i != chain_nr) {
struct branch_stack *lbr_stack = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
int lbr_nr = lbr_stack->nr, j, k;
bool branch;
struct branch_flags *flags;
ip = chain->ips[j];
else if (j > i + 1) {
k = j - i - 2;
- ip = lbr_stack->entries[k].from;
+ ip = entries[k].from;
branch = true;
- flags = &lbr_stack->entries[k].flags;
+ flags = &entries[k].flags;
} else {
- ip = lbr_stack->entries[0].to;
+ ip = entries[0].to;
branch = true;
- flags = &lbr_stack->entries[0].flags;
- branch_from =
- lbr_stack->entries[0].from;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
}
} else {
if (j < lbr_nr) {
k = lbr_nr - j - 1;
- ip = lbr_stack->entries[k].from;
+ ip = entries[k].from;
branch = true;
- flags = &lbr_stack->entries[k].flags;
+ flags = &entries[k].flags;
}
else if (j > lbr_nr)
ip = chain->ips[i + 1 - (j - lbr_nr)];
else {
- ip = lbr_stack->entries[0].to;
+ ip = entries[0].to;
branch = true;
- flags = &lbr_stack->entries[0].flags;
- branch_from =
- lbr_stack->entries[0].from;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
}
}
int max_stack)
{
struct branch_stack *branch = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
struct ip_callchain *chain = sample->callchain;
int chain_nr = 0;
u8 cpumode = PERF_RECORD_MISC_USER;
for (i = 0; i < nr; i++) {
if (callchain_param.order == ORDER_CALLEE) {
- be[i] = branch->entries[i];
+ be[i] = entries[i];
if (chain == NULL)
continue;
be[i].from >= chain->ips[first_call] - 8)
first_call++;
} else
- be[i] = branch->entries[branch->nr - i - 1];
+ be[i] = entries[branch->nr - i - 1];
}
memset(iter, 0, sizeof(struct iterations) * nr);
struct thread *thread)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist;
u64 i;
Py_FatalError("couldn't create Python dictionary");
pydict_set_item_string_decref(pyelem, "from",
- PyLong_FromUnsignedLongLong(br->entries[i].from));
+ PyLong_FromUnsignedLongLong(entries[i].from));
pydict_set_item_string_decref(pyelem, "to",
- PyLong_FromUnsignedLongLong(br->entries[i].to));
+ PyLong_FromUnsignedLongLong(entries[i].to));
pydict_set_item_string_decref(pyelem, "mispred",
- PyBool_FromLong(br->entries[i].flags.mispred));
+ PyBool_FromLong(entries[i].flags.mispred));
pydict_set_item_string_decref(pyelem, "predicted",
- PyBool_FromLong(br->entries[i].flags.predicted));
+ PyBool_FromLong(entries[i].flags.predicted));
pydict_set_item_string_decref(pyelem, "in_tx",
- PyBool_FromLong(br->entries[i].flags.in_tx));
+ PyBool_FromLong(entries[i].flags.in_tx));
pydict_set_item_string_decref(pyelem, "abort",
- PyBool_FromLong(br->entries[i].flags.abort));
+ PyBool_FromLong(entries[i].flags.abort));
pydict_set_item_string_decref(pyelem, "cycles",
- PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+ PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
thread__find_map_fb(thread, sample->cpumode,
- br->entries[i].from, &al);
+ entries[i].from, &al);
dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "from_dsoname",
_PyUnicode_FromString(dsoname));
thread__find_map_fb(thread, sample->cpumode,
- br->entries[i].to, &al);
+ entries[i].to, &al);
dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "to_dsoname",
_PyUnicode_FromString(dsoname));
struct thread *thread)
{
struct branch_stack *br = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist;
u64 i;
char bf[512];
Py_FatalError("couldn't create Python dictionary");
thread__find_symbol_fb(thread, sample->cpumode,
- br->entries[i].from, &al);
+ entries[i].from, &al);
get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "from",
_PyUnicode_FromString(bf));
thread__find_symbol_fb(thread, sample->cpumode,
- br->entries[i].to, &al);
+ entries[i].to, &al);
get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "to",
_PyUnicode_FromString(bf));
- get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+ get_br_mspred(&entries[i].flags, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "pred",
_PyUnicode_FromString(bf));
- if (br->entries[i].flags.in_tx) {
+ if (entries[i].flags.in_tx) {
pydict_set_item_string_decref(pyelem, "in_tx",
_PyUnicode_FromString("X"));
} else {
_PyUnicode_FromString("-"));
}
- if (br->entries[i].flags.abort) {
+ if (entries[i].flags.abort) {
pydict_set_item_string_decref(pyelem, "abort",
_PyUnicode_FromString("A"));
} else {
{
struct ip_callchain *callchain = sample->callchain;
struct branch_stack *lbr_stack = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 kernel_callchain_nr = callchain->nr;
unsigned int i;
i, callchain->ips[i]);
printf("..... %2d: %016" PRIx64 "\n",
- (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+ (int)(kernel_callchain_nr), entries[0].to);
for (i = 0; i < lbr_stack->nr; i++)
printf("..... %2d: %016" PRIx64 "\n",
- (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+ (int)(i + kernel_callchain_nr + 1), entries[i].from);
}
}
static void branch_stack__printf(struct perf_sample *sample, bool callstack)
{
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
uint64_t i;
printf("%s: nr:%" PRIu64 "\n",
sample->branch_stack->nr);
for (i = 0; i < sample->branch_stack->nr; i++) {
- struct branch_entry *e = &sample->branch_stack->entries[i];
+ struct branch_entry *e = &entries[i];
if (!callstack) {
printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- sz += sizeof(u64);
+ /* nr, hw_idx */
+ sz += 2 * sizeof(u64);
result += sz;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- sz += sizeof(u64);
+ /* nr, hw_idx */
+ sz += 2 * sizeof(u64);
memcpy(array, sample->branch_stack, sz);
array = (void *)array + sz;
}