mirrors/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2025-11-04 10:40:15 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

perf tools: Add hw_idx in struct branch_stack

Browse source 
The low level index of raw branch records for the most recent branch can
be recorded in a sample with PERF_SAMPLE_BRANCH_HW_INDEX
branch_sample_type. Extend struct branch_stack to support it.

However, if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, only nr and
entries[] will be output by kernel. The pointer of entries[] could be
wrong, since the output format is different with new struct
branch_stack.  Add a variable no_hw_idx in struct perf_sample to
indicate whether the hw_idx is output.  Add get_branch_entry() to return
corresponding pointer of entries[0].

To make dummy branch sample consistent as new branch sample, add hw_idx
in struct dummy_branch_stack for cs-etm and intel-pt.

Apply the new struct branch_stack for synthetic events as well.

Extend test case sample-parsing to support new struct branch_stack.

Committer notes:

Renamed get_branch_entries() to perf_sample__branch_entries() to have
proper namespacing and pave the way for this to be moved to libperf,
eventually.

Add 'static' to that inline as it is in a header.

Add 'hw_idx' to 'struct dummy_branch_stack' in cs-etm.c to fix the build
on arm64.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200228163011.19358-2-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Kan Liang 2020-02-28 08:30:00 -08:00 committed by Arnaldo Carvalho de Melo
parent 6339998d22
commit 42bbabed09
13 changed files with 125 additions and 71 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

70
tools/perf/builtin-script.c
View file

@ -735,6 +735,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp) struct perf_event_attr *attr, FILE *fp)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt; struct addr_location alf, alt;
u64 i, from, to; u64 i, from, to;
int printed = 0; int printed = 0;
@ -743,8 +744,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
return 0; return 0;
for (i = 0; i < br->nr; i++) { for (i = 0; i < br->nr; i++) {
from = br->entries[i].from; from = entries[i].from;
to = br->entries[i].to; to = entries[i].to;
if (PRINT_FIELD(DSO)) { if (PRINT_FIELD(DSO)) {
memset(&alf, 0, sizeof(alf)); memset(&alf, 0, sizeof(alf));
@ -768,10 +769,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
} }
printed += fprintf(fp, "/%c/%c/%c/%d ", printed += fprintf(fp, "/%c/%c/%c/%d ",
mispred_str( br->entries + i), mispred_str(entries + i),
br->entries[i].flags.in_tx? 'X' : '-', entries[i].flags.in_tx ? 'X' : '-',
br->entries[i].flags.abort? 'A' : '-', entries[i].flags.abort ? 'A' : '-',
br->entries[i].flags.cycles); entries[i].flags.cycles);
} }
return printed; return printed;
@ -782,6 +783,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp) struct perf_event_attr *attr, FILE *fp)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt; struct addr_location alf, alt;
u64 i, from, to; u64 i, from, to;
int printed = 0; int printed = 0;
@ -793,8 +795,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
memset(&alf, 0, sizeof(alf)); memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt)); memset(&alt, 0, sizeof(alt));
from = br->entries[i].from; from = entries[i].from;
to = br->entries[i].to; to = entries[i].to;
thread__find_symbol_fb(thread, sample->cpumode, from, &alf); thread__find_symbol_fb(thread, sample->cpumode, from, &alf);
thread__find_symbol_fb(thread, sample->cpumode, to, &alt); thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
@ -813,10 +815,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
printed += fprintf(fp, ")"); printed += fprintf(fp, ")");
} }
printed += fprintf(fp, "/%c/%c/%c/%d ", printed += fprintf(fp, "/%c/%c/%c/%d ",
mispred_str( br->entries + i), mispred_str(entries + i),
br->entries[i].flags.in_tx? 'X' : '-', entries[i].flags.in_tx ? 'X' : '-',
br->entries[i].flags.abort? 'A' : '-', entries[i].flags.abort ? 'A' : '-',
br->entries[i].flags.cycles); entries[i].flags.cycles);
} }
return printed; return printed;
@ -827,6 +829,7 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp) struct perf_event_attr *attr, FILE *fp)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
struct addr_location alf, alt; struct addr_location alf, alt;
u64 i, from, to; u64 i, from, to;
int printed = 0; int printed = 0;
@ -838,8 +841,8 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
memset(&alf, 0, sizeof(alf)); memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt)); memset(&alt, 0, sizeof(alt));
from = br->entries[i].from; from = entries[i].from;
to = br->entries[i].to; to = entries[i].to;
if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&
!alf.map->dso->adjust_symbols) !alf.map->dso->adjust_symbols)
@ -862,10 +865,10 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
printed += fprintf(fp, ")"); printed += fprintf(fp, ")");
} }
printed += fprintf(fp, "/%c/%c/%c/%d ", printed += fprintf(fp, "/%c/%c/%c/%d ",
mispred_str(br->entries + i), mispred_str(entries + i),
br->entries[i].flags.in_tx ? 'X' : '-', entries[i].flags.in_tx ? 'X' : '-',
br->entries[i].flags.abort ? 'A' : '-', entries[i].flags.abort ? 'A' : '-',
br->entries[i].flags.cycles); entries[i].flags.cycles);
} }
return printed; return printed;
@ -1053,6 +1056,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
struct machine *machine, FILE *fp) struct machine *machine, FILE *fp)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 start, end; u64 start, end;
int i, insn, len, nr, ilen, printed = 0; int i, insn, len, nr, ilen, printed = 0;
struct perf_insn x; struct perf_insn x;
@ -1073,31 +1077,31 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += fprintf(fp, "%c", '\n'); printed += fprintf(fp, "%c", '\n');
/* Handle first from jump, of which we don't know the entry. */ /* Handle first from jump, of which we don't know the entry. */
len = grab_bb(buffer, br->entries[nr-1].from, len = grab_bb(buffer, entries[nr-1].from,
br->entries[nr-1].from, entries[nr-1].from,
machine, thread, &x.is64bit, &x.cpumode, false); machine, thread, &x.is64bit, &x.cpumode, false);
if (len > 0) { 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); 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); &x, buffer, len, 0, fp, &total_cycles);
if (PRINT_FIELD(SRCCODE)) 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 */ /* Print all blocks */
for (i = nr - 2; i >= 0; i--) { 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, pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
br->entries[i].from, entries[i].from,
br->entries[i].to); entries[i].to);
start = br->entries[i + 1].to; start = entries[i + 1].to;
end = br->entries[i].from; end = entries[i].from;
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
/* Patch up missing kernel transfers due to ring filters */ /* Patch up missing kernel transfers due to ring filters */
if (len == -ENXIO && i > 0) { if (len == -ENXIO && i > 0) {
end = br->entries[--i].from; end = entries[--i].from;
pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end); pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
} }
@ -1110,7 +1114,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) { 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); &total_cycles);
if (PRINT_FIELD(SRCCODE)) if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, ip); printed += print_srccode(thread, x.cpumode, ip);
@ -1134,9 +1138,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
* Hit the branch? In this case we are already done, and the target * Hit the branch? In this case we are already done, and the target
* has not been executed yet. * has not been executed yet.
*/ */
if (br->entries[0].from == sample->ip) if (entries[0].from == sample->ip)
goto out; goto out;
if (br->entries[0].flags.abort) if (entries[0].flags.abort)
goto out; goto out;
/* /*
@ -1147,7 +1151,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
* between final branch and sample. When this happens just * between final branch and sample. When this happens just
* continue walking after the last TO until we hit a branch. * continue walking after the last TO until we hit a branch.
*/ */
start = br->entries[0].to; start = entries[0].to;
end = sample->ip; end = sample->ip;
if (end < start) { if (end < start) {
/* Missing jump. Scan 128 bytes for the next branch */ /* Missing jump. Scan 128 bytes for the next branch */

7
tools/perf/tests/sample-parsing.c
View file

@ -99,6 +99,7 @@ static bool samples_same(const struct perf_sample *s1,
if (type & PERF_SAMPLE_BRANCH_STACK) { if (type & PERF_SAMPLE_BRANCH_STACK) {
COMP(branch_stack->nr); COMP(branch_stack->nr);
COMP(branch_stack->hw_idx);
for (i = 0; i < s1->branch_stack->nr; i++) for (i = 0; i < s1->branch_stack->nr; i++)
MCOMP(branch_stack->entries[i]); MCOMP(branch_stack->entries[i]);
} }
@ -186,7 +187,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
u64 data[64]; u64 data[64];
} branch_stack = { } branch_stack = {
/* 1 branch_entry */ /* 1 branch_entry */
.data = {1, 211, 212, 213}, .data = {1, -1ULL, 211, 212, 213},
}; };
u64 regs[64]; u64 regs[64];
const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL}; const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
@ -208,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
.transaction = 112, .transaction = 112,
.raw_data = (void *)raw_data, .raw_data = (void *)raw_data,
.callchain = &callchain.callchain, .callchain = &callchain.callchain,
.no_hw_idx = false,
.branch_stack = &branch_stack.branch_stack, .branch_stack = &branch_stack.branch_stack,
.user_regs = { .user_regs = {
.abi = PERF_SAMPLE_REGS_ABI_64, .abi = PERF_SAMPLE_REGS_ABI_64,
@ -244,6 +246,9 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
if (sample_type & PERF_SAMPLE_REGS_INTR) if (sample_type & PERF_SAMPLE_REGS_INTR)
evsel.core.attr.sample_regs_intr = sample_regs; 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++) for (i = 0; i < sizeof(regs); i++)
*(i + (u8 *)regs) = i & 0xfe; *(i + (u8 *)regs) = i & 0xfe;

22
tools/perf/util/branch.h
View file

@ -12,6 +12,7 @@
#include <linux/stddef.h> #include <linux/stddef.h>
#include <linux/perf_event.h> #include <linux/perf_event.h>
#include <linux/types.h> #include <linux/types.h>
#include "event.h"
struct branch_flags { struct branch_flags {
u64 mispred:1; u64 mispred:1;
@ -39,9 +40,30 @@ struct branch_entry {
struct branch_stack { struct branch_stack {
u64 nr; u64 nr;
u64 hw_idx;
struct branch_entry entries[0]; 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 { struct branch_type_stat {
bool branch_to; bool branch_to;
u64 counts[PERF_BR_MAX]; u64 counts[PERF_BR_MAX];

2
tools/perf/util/cs-etm.c
View file

@ -1172,6 +1172,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
union perf_event *event = tidq->event_buf; union perf_event *event = tidq->event_buf;
struct dummy_branch_stack { struct dummy_branch_stack {
u64 nr; u64 nr;
u64 hw_idx;
struct branch_entry entries; struct branch_entry entries;
} dummy_bs; } dummy_bs;
u64 ip; u64 ip;
@ -1202,6 +1203,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
if (etm->synth_opts.last_branch) { if (etm->synth_opts.last_branch) {
dummy_bs = (struct dummy_branch_stack){ dummy_bs = (struct dummy_branch_stack){
.nr = 1, .nr = 1,
.hw_idx = -1ULL,
.entries = { .entries = {
.from = sample.ip, .from = sample.ip,
.to = sample.addr, .to = sample.addr,

1
tools/perf/util/event.h
View file

@ -139,6 +139,7 @@ struct perf_sample {
u16 insn_len; u16 insn_len;
u8 cpumode; u8 cpumode;
u16 misc; u16 misc;
bool no_hw_idx; /* No hw_idx collected in branch_stack */
char insn[MAX_INSN]; char insn[MAX_INSN];
void *raw_data; void *raw_data;
struct ip_callchain *callchain; struct ip_callchain *callchain;

5
tools/perf/util/evsel.c
View file

@ -2169,7 +2169,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
if (data->branch_stack->nr > max_branch_nr) if (data->branch_stack->nr > max_branch_nr)
return -EFAULT; return -EFAULT;
sz = data->branch_stack->nr * sizeof(struct branch_entry); 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); OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz; array = (void *)array + sz;
} }

5
tools/perf/util/evsel.h
View file

@ -389,6 +389,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; 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) static inline bool evsel__has_callchain(const struct evsel *evsel)
{ {
return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;

3
tools/perf/util/hist.c
View file

@ -2584,9 +2584,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
u64 *total_cycles) u64 *total_cycles)
{ {
struct branch_info *bi; struct branch_info *bi;
struct branch_entry *entries = perf_sample__branch_entries(sample);
/* If we have branch cycles always annotate them. */ /* 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; int i;
bi = sample__resolve_bstack(sample, al); bi = sample__resolve_bstack(sample, al);

2
tools/perf/util/intel-pt.c
View file

@ -1295,6 +1295,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
struct perf_sample sample = { .ip = 0, }; struct perf_sample sample = { .ip = 0, };
struct dummy_branch_stack { struct dummy_branch_stack {
u64 nr; u64 nr;
u64 hw_idx;
struct branch_entry entries; struct branch_entry entries;
} dummy_bs; } dummy_bs;
@ -1316,6 +1317,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) { if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
dummy_bs = (struct dummy_branch_stack){ dummy_bs = (struct dummy_branch_stack){
.nr = 1, .nr = 1,
.hw_idx = -1ULL,
.entries = { .entries = {
.from = sample.ip, .from = sample.ip,
.to = sample.addr, .to = sample.addr,

35
tools/perf/util/machine.c
View file

@ -2081,15 +2081,16 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
{ {
unsigned int i; unsigned int i;
const struct branch_stack *bs = sample->branch_stack; 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)); struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
if (!bi) if (!bi)
return NULL; return NULL;
for (i = 0; i < bs->nr; i++) { 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].to, entries[i].to);
ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from); ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
bi[i].flags = bs->entries[i].flags; bi[i].flags = entries[i].flags;
} }
return bi; return bi;
} }
@ -2185,6 +2186,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
/* LBR only affects the user callchain */ /* LBR only affects the user callchain */
if (i != chain_nr) { if (i != chain_nr) {
struct branch_stack *lbr_stack = sample->branch_stack; 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; int lbr_nr = lbr_stack->nr, j, k;
bool branch; bool branch;
struct branch_flags *flags; struct branch_flags *flags;
@ -2210,31 +2212,29 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
ip = chain->ips[j]; ip = chain->ips[j];
else if (j > i + 1) { else if (j > i + 1) {
k = j - i - 2; k = j - i - 2;
ip = lbr_stack->entries[k].from; ip = entries[k].from;
branch = true; branch = true;
flags = &lbr_stack->entries[k].flags; flags = &entries[k].flags;
} else { } else {
ip = lbr_stack->entries[0].to; ip = entries[0].to;
branch = true; branch = true;
flags = &lbr_stack->entries[0].flags; flags = &entries[0].flags;
branch_from = branch_from = entries[0].from;
lbr_stack->entries[0].from;
} }
} else { } else {
if (j < lbr_nr) { if (j < lbr_nr) {
k = lbr_nr - j - 1; k = lbr_nr - j - 1;
ip = lbr_stack->entries[k].from; ip = entries[k].from;
branch = true; branch = true;
flags = &lbr_stack->entries[k].flags; flags = &entries[k].flags;
} }
else if (j > lbr_nr) else if (j > lbr_nr)
ip = chain->ips[i + 1 - (j - lbr_nr)]; ip = chain->ips[i + 1 - (j - lbr_nr)];
else { else {
ip = lbr_stack->entries[0].to; ip = entries[0].to;
branch = true; branch = true;
flags = &lbr_stack->entries[0].flags; flags = &entries[0].flags;
branch_from = branch_from = entries[0].from;
lbr_stack->entries[0].from;
} }
} }
@ -2281,6 +2281,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
int max_stack) int max_stack)
{ {
struct branch_stack *branch = sample->branch_stack; struct branch_stack *branch = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
struct ip_callchain *chain = sample->callchain; struct ip_callchain *chain = sample->callchain;
int chain_nr = 0; int chain_nr = 0;
u8 cpumode = PERF_RECORD_MISC_USER; u8 cpumode = PERF_RECORD_MISC_USER;
@ -2328,7 +2329,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
for (i = 0; i < nr; i++) { for (i = 0; i < nr; i++) {
if (callchain_param.order == ORDER_CALLEE) { if (callchain_param.order == ORDER_CALLEE) {
be[i] = branch->entries[i]; be[i] = entries[i];
if (chain == NULL) if (chain == NULL)
continue; continue;
@ -2347,7 +2348,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
be[i].from >= chain->ips[first_call] - 8) be[i].from >= chain->ips[first_call] - 8)
first_call++; first_call++;
} else } else
be[i] = branch->entries[branch->nr - i - 1]; be[i] = entries[branch->nr - i - 1];
} }
memset(iter, 0, sizeof(struct iterations) * nr); memset(iter, 0, sizeof(struct iterations) * nr);

30
tools/perf/util/scripting-engines/trace-event-python.c
View file

@ -464,6 +464,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
struct thread *thread) struct thread *thread)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist; PyObject *pylist;
u64 i; u64 i;
@ -484,28 +485,28 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
Py_FatalError("couldn't create Python dictionary"); Py_FatalError("couldn't create Python dictionary");
pydict_set_item_string_decref(pyelem, "from", 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", 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", 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", 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", 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", 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", 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, thread__find_map_fb(thread, sample->cpumode,
br->entries[i].from, &al); entries[i].from, &al);
dsoname = get_dsoname(al.map); dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "from_dsoname", pydict_set_item_string_decref(pyelem, "from_dsoname",
_PyUnicode_FromString(dsoname)); _PyUnicode_FromString(dsoname));
thread__find_map_fb(thread, sample->cpumode, thread__find_map_fb(thread, sample->cpumode,
br->entries[i].to, &al); entries[i].to, &al);
dsoname = get_dsoname(al.map); dsoname = get_dsoname(al.map);
pydict_set_item_string_decref(pyelem, "to_dsoname", pydict_set_item_string_decref(pyelem, "to_dsoname",
_PyUnicode_FromString(dsoname)); _PyUnicode_FromString(dsoname));
@ -561,6 +562,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
struct thread *thread) struct thread *thread)
{ {
struct branch_stack *br = sample->branch_stack; struct branch_stack *br = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
PyObject *pylist; PyObject *pylist;
u64 i; u64 i;
char bf[512]; char bf[512];
@ -581,22 +583,22 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
Py_FatalError("couldn't create Python dictionary"); Py_FatalError("couldn't create Python dictionary");
thread__find_symbol_fb(thread, sample->cpumode, 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)); get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "from", pydict_set_item_string_decref(pyelem, "from",
_PyUnicode_FromString(bf)); _PyUnicode_FromString(bf));
thread__find_symbol_fb(thread, sample->cpumode, 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)); get_symoff(al.sym, &al, true, bf, sizeof(bf));
pydict_set_item_string_decref(pyelem, "to", pydict_set_item_string_decref(pyelem, "to",
_PyUnicode_FromString(bf)); _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", pydict_set_item_string_decref(pyelem, "pred",
_PyUnicode_FromString(bf)); _PyUnicode_FromString(bf));
if (br->entries[i].flags.in_tx) { if (entries[i].flags.in_tx) {
pydict_set_item_string_decref(pyelem, "in_tx", pydict_set_item_string_decref(pyelem, "in_tx",
_PyUnicode_FromString("X")); _PyUnicode_FromString("X"));
} else { } else {
@ -604,7 +606,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
_PyUnicode_FromString("-")); _PyUnicode_FromString("-"));
} }
if (br->entries[i].flags.abort) { if (entries[i].flags.abort) {
pydict_set_item_string_decref(pyelem, "abort", pydict_set_item_string_decref(pyelem, "abort",
_PyUnicode_FromString("A")); _PyUnicode_FromString("A"));
} else { } else {

8
tools/perf/util/session.c
View file

@ -1007,6 +1007,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
{ {
struct ip_callchain *callchain = sample->callchain; struct ip_callchain *callchain = sample->callchain;
struct branch_stack *lbr_stack = sample->branch_stack; struct branch_stack *lbr_stack = sample->branch_stack;
struct branch_entry *entries = perf_sample__branch_entries(sample);
u64 kernel_callchain_nr = callchain->nr; u64 kernel_callchain_nr = callchain->nr;
unsigned int i; unsigned int i;
@ -1043,10 +1044,10 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
i, callchain->ips[i]); i, callchain->ips[i]);
printf("..... %2d: %016" PRIx64 "\n", 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++) for (i = 0; i < lbr_stack->nr; i++)
printf("..... %2d: %016" PRIx64 "\n", 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);
} }
} }
@ -1068,6 +1069,7 @@ static void callchain__printf(struct evsel *evsel,
static void branch_stack__printf(struct perf_sample *sample, bool callstack) static void branch_stack__printf(struct perf_sample *sample, bool callstack)
{ {
struct branch_entry *entries = perf_sample__branch_entries(sample);
uint64_t i; uint64_t i;
printf("%s: nr:%" PRIu64 "\n", printf("%s: nr:%" PRIu64 "\n",
@ -1075,7 +1077,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
sample->branch_stack->nr); sample->branch_stack->nr);
for (i = 0; i < sample->branch_stack->nr; i++) { 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) { if (!callstack) {
printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",

6
tools/perf/util/synthetic-events.c
View file

@ -1183,7 +1183,8 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
if (type & PERF_SAMPLE_BRANCH_STACK) { if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry); sz = sample->branch_stack->nr * sizeof(struct branch_entry);
sz += sizeof(u64); /* nr, hw_idx */
sz += 2 * sizeof(u64);
result += sz; result += sz;
} }
@ -1344,7 +1345,8 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
if (type & PERF_SAMPLE_BRANCH_STACK) { if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry); 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); memcpy(array, sample->branch_stack, sz);
array = (void *)array + sz; array = (void *)array + sz;
} }