Merge branch 'perf/hw-branch-sampling' into perf/core

Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Ingo Molnar
2012-03-12 20:46:35 +01:00
33 changed files with 2019 additions and 245 deletions

View File

@@ -152,6 +152,36 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
corresponding events, i.e., they always refer to events defined earlier on the command
line.
-b::
--branch-any::
Enable taken branch stack sampling. Any type of taken branch may be sampled.
This is a shortcut for --branch-filter any. See --branch-filter for more infos.
-j::
--branch-filter::
Enable taken branch stack sampling. Each sample captures a series of consecutive
taken branches. The number of branches captured with each sample depends on the
underlying hardware, the type of branches of interest, and the executed code.
It is possible to select the types of branches captured by enabling filters. The
following filters are defined:
- any: any type of branches
- any_call: any function call or system call
- any_ret: any function return or system call return
- any_ind: any indirect branch
- u: only when the branch target is at the user level
- k: only when the branch target is in the kernel
- hv: only when the target is at the hypervisor level
+
The option requires at least one branch type among any, any_call, any_ret, ind_call.
The privilege levels may be ommitted, in which case, the privilege levels of the associated
event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
levels are subject to permissions. When sampling on multiple events, branch stack sampling
is enabled for all the sampling events. The sampled branch type is the same for all events.
The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
Note that this feature may not be available on all processors.
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]

View File

@@ -153,6 +153,16 @@ OPTIONS
information which may be very large and thus may clutter the display.
It currently includes: cpu and numa topology of the host system.
-b::
--branch-stack::
Use the addresses of sampled taken branches instead of the instruction
address to build the histograms. To generate meaningful output, the
perf.data file must have been obtained using perf record -b or
perf record --branch-filter xxx where xxx is a branch filter option.
perf report is able to auto-detect whether a perf.data file contains
branch stacks and it will automatically switch to the branch view mode,
unless --no-branch-stack is used.
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-annotate[1]

View File

@@ -473,6 +473,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
if (!have_tracepoints(&evsel_list->entries))
perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
if (!rec->file_new) {
err = perf_session__read_header(session, output);
if (err < 0)
@@ -638,6 +641,90 @@ out_delete_session:
return err;
}
#define BRANCH_OPT(n, m) \
{ .name = n, .mode = (m) }
#define BRANCH_END { .name = NULL }
struct branch_mode {
const char *name;
int mode;
};
static const struct branch_mode branch_modes[] = {
BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
BRANCH_END
};
static int
parse_branch_stack(const struct option *opt, const char *str, int unset)
{
#define ONLY_PLM \
(PERF_SAMPLE_BRANCH_USER |\
PERF_SAMPLE_BRANCH_KERNEL |\
PERF_SAMPLE_BRANCH_HV)
uint64_t *mode = (uint64_t *)opt->value;
const struct branch_mode *br;
char *s, *os = NULL, *p;
int ret = -1;
if (unset)
return 0;
/*
* cannot set it twice, -b + --branch-filter for instance
*/
if (*mode)
return -1;
/* str may be NULL in case no arg is passed to -b */
if (str) {
/* because str is read-only */
s = os = strdup(str);
if (!s)
return -1;
for (;;) {
p = strchr(s, ',');
if (p)
*p = '\0';
for (br = branch_modes; br->name; br++) {
if (!strcasecmp(s, br->name))
break;
}
if (!br->name) {
ui__warning("unknown branch filter %s,"
" check man page\n", s);
goto error;
}
*mode |= br->mode;
if (!p)
break;
s = p + 1;
}
}
ret = 0;
/* default to any branch */
if ((*mode & ~ONLY_PLM) == 0) {
*mode = PERF_SAMPLE_BRANCH_ANY;
}
error:
free(os);
return ret;
}
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -727,6 +814,14 @@ const struct option record_options[] = {
"monitor event in cgroup name only",
parse_cgroups),
OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
"branch any", "sample any taken branches",
parse_branch_stack),
OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
"branch filter mask", "branch stack filter modes",
parse_branch_stack),
OPT_END()
};

View File

@@ -53,6 +53,82 @@ struct perf_report {
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
struct addr_location *al,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
struct perf_report *rep = container_of(tool, struct perf_report, tool);
struct symbol *parent = NULL;
int err = 0;
unsigned i;
struct hist_entry *he;
struct branch_info *bi, *bx;
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
sample->callchain, &parent);
if (err)
return err;
}
bi = machine__resolve_bstack(machine, al->thread,
sample->branch_stack);
if (!bi)
return -ENOMEM;
for (i = 0; i < sample->branch_stack->nr; i++) {
if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
continue;
/*
* The report shows the percentage of total branches captured
* and not events sampled. Thus we use a pseudo period of 1.
*/
he = __hists__add_branch_entry(&evsel->hists, al, parent,
&bi[i], 1);
if (he) {
struct annotation *notes;
err = -ENOMEM;
bx = he->branch_info;
if (bx->from.sym && use_browser > 0) {
notes = symbol__annotation(bx->from.sym);
if (!notes->src
&& symbol__alloc_hist(bx->from.sym) < 0)
goto out;
err = symbol__inc_addr_samples(bx->from.sym,
bx->from.map,
evsel->idx,
bx->from.al_addr);
if (err)
goto out;
}
if (bx->to.sym && use_browser > 0) {
notes = symbol__annotation(bx->to.sym);
if (!notes->src
&& symbol__alloc_hist(bx->to.sym) < 0)
goto out;
err = symbol__inc_addr_samples(bx->to.sym,
bx->to.map,
evsel->idx,
bx->to.al_addr);
if (err)
goto out;
}
evsel->hists.stats.total_period += 1;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
err = 0;
} else
return -ENOMEM;
}
out:
return err;
}
static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
struct addr_location *al,
struct perf_sample *sample,
@@ -126,14 +202,21 @@ static int process_sample_event(struct perf_tool *tool,
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
return 0;
if (al.map != NULL)
al.map->dso->hit = 1;
if (sort__branch_mode == 1) {
if (perf_report__add_branch_hist_entry(tool, &al, sample,
evsel, machine)) {
pr_debug("problem adding lbr entry, skipping event\n");
return -1;
}
} else {
if (al.map != NULL)
al.map->dso->hit = 1;
if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
pr_debug("problem incrementing symbol period, skipping event\n");
return -1;
if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
pr_debug("problem incrementing symbol period, skipping event\n");
return -1;
}
}
return 0;
}
@@ -188,6 +271,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
}
}
if (sort__branch_mode == 1) {
if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
fprintf(stderr, "selected -b but no branch data."
" Did you call perf record without"
" -b?\n");
return -1;
}
}
return 0;
}
@@ -246,7 +338,7 @@ static int __cmd_report(struct perf_report *rep)
{
int ret = -EINVAL;
u64 nr_samples;
struct perf_session *session;
struct perf_session *session = rep->session;
struct perf_evsel *pos;
struct map *kernel_map;
struct kmap *kernel_kmap;
@@ -254,13 +346,6 @@ static int __cmd_report(struct perf_report *rep)
signal(SIGINT, sig_handler);
session = perf_session__new(rep->input_name, O_RDONLY,
rep->force, false, &rep->tool);
if (session == NULL)
return -ENOMEM;
rep->session = session;
if (rep->cpu_list) {
ret = perf_session__cpu_bitmap(session, rep->cpu_list,
rep->cpu_bitmap);
@@ -427,9 +512,19 @@ setup:
return 0;
}
static int
parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
{
sort__branch_mode = !unset;
return 0;
}
int cmd_report(int argc, const char **argv, const char *prefix __used)
{
struct perf_session *session;
struct stat st;
bool has_br_stack = false;
int ret = -1;
char callchain_default_opt[] = "fractal,0.5,callee";
const char * const report_usage[] = {
"perf report [<options>]",
@@ -477,7 +572,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
OPT_BOOLEAN(0, "stdio", &report.use_stdio,
"Use the stdio interface"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
"sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
" dso_from, symbol_to, symbol_from, mispredict"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -517,6 +613,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
"Specify disassembler style (e.g. -M intel for intel syntax)"),
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
"Show a column with the sum of periods"),
OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
"use branch records for histogram filling", parse_branch_mode),
OPT_END()
};
@@ -536,11 +634,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
else
report.input_name = "perf.data";
}
session = perf_session__new(report.input_name, O_RDONLY,
report.force, false, &report.tool);
if (session == NULL)
return -ENOMEM;
if (strcmp(report.input_name, "-") != 0)
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
HEADER_BRANCH_STACK);
if (sort__branch_mode == -1 && has_br_stack)
sort__branch_mode = 1;
/* sort__branch_mode could be 0 if --no-branch-stack */
if (sort__branch_mode == 1) {
/*
* if no sort_order is provided, then specify
* branch-mode specific order
*/
if (sort_order == default_sort_order)
sort_order = "comm,dso_from,symbol_from,"
"dso_to,symbol_to";
}
if (strcmp(report.input_name, "-") != 0) {
setup_browser(true);
else
} else {
use_browser = 0;
}
/*
* Only in the newt browser we are doing integrated annotation,
@@ -568,13 +691,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
}
if (symbol__init() < 0)
return -1;
goto error;
setup_sorting(report_usage, options);
if (parent_pattern != default_parent_pattern) {
if (sort_dimension__add("parent") < 0)
return -1;
goto error;
/*
* Only show the parent fields if we explicitly
@@ -592,9 +715,20 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
if (argc)
usage_with_options(report_usage, options);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
return __cmd_report(&report);
if (sort__branch_mode == 1) {
sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
} else {
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
}
ret = __cmd_report(&report);
error:
perf_session__delete(session);
return ret;
}

View File

@@ -179,6 +179,23 @@ struct ip_callchain {
u64 ips[0];
};
struct branch_flags {
u64 mispred:1;
u64 predicted:1;
u64 reserved:62;
};
struct branch_entry {
u64 from;
u64 to;
struct branch_flags flags;
};
struct branch_stack {
u64 nr;
struct branch_entry entries[0];
};
extern bool perf_host, perf_guest;
extern const char perf_version_string[];
@@ -205,6 +222,7 @@ struct perf_record_opts {
unsigned int freq;
unsigned int mmap_pages;
unsigned int user_freq;
int branch_stack;
u64 default_interval;
u64 user_interval;
const char *cpu_list;

View File

@@ -81,6 +81,7 @@ struct perf_sample {
u32 raw_size;
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
};
#define BUILD_ID_SIZE 20

View File

@@ -126,6 +126,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
attr->watermark = 0;
attr->wakeup_events = 1;
}
if (opts->branch_stack) {
attr->sample_type |= PERF_SAMPLE_BRANCH_STACK;
attr->branch_sample_type = opts->branch_stack;
}
attr->mmap = track;
attr->comm = track;
@@ -576,6 +580,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
data->raw_data = (void *) pdata;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
u64 sz;
data->branch_stack = (struct branch_stack *)array;
array++; /* nr */
sz = data->branch_stack->nr * sizeof(struct branch_entry);
sz /= sizeof(u64);
array += sz;
}
return 0;
}

View File

@@ -1023,6 +1023,12 @@ write_it:
return do_write_string(fd, buffer);
}
static int write_branch_stack(int fd __used, struct perf_header *h __used,
struct perf_evlist *evlist __used)
{
return 0;
}
static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
{
char *str = do_read_string(fd, ph);
@@ -1144,8 +1150,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
uint64_t id;
void *buf = NULL;
char *str;
u32 nre, sz, nr, i, j, msz;
int ret;
u32 nre, sz, nr, i, j;
ssize_t ret;
size_t msz;
/* number of events */
ret = read(fd, &nre, sizeof(nre));
@@ -1162,25 +1169,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
if (ph->needs_swap)
sz = bswap_32(sz);
/*
* ensure it is at least to our ABI rev
*/
if (sz < (u32)sizeof(attr))
goto error;
memset(&attr, 0, sizeof(attr));
/* read entire region to sync up to next field */
/* buffer to hold on file attr struct */
buf = malloc(sz);
if (!buf)
goto error;
msz = sizeof(attr);
if (sz < msz)
if (sz < (ssize_t)msz)
msz = sz;
for (i = 0 ; i < nre; i++) {
/*
* must read entire on-file attr struct to
* sync up with layout.
*/
ret = read(fd, buf, sz);
if (ret != (ssize_t)sz)
goto error;
@@ -1316,6 +1321,12 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
free(str);
}
static void print_branch_stack(struct perf_header *ph __used, int fd __used,
FILE *fp)
{
fprintf(fp, "# contains samples with branch stack\n");
}
static int __event_process_build_id(struct build_id_event *bev,
char *filename,
struct perf_session *session)
@@ -1520,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPA(HEADER_CMDLINE, cmdline),
FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology),
FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology),
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
};
struct header_print_data {
@@ -1804,35 +1816,101 @@ out_free:
return err;
}
static int check_magic_endian(u64 *magic, struct perf_file_header *header,
struct perf_header *ph)
static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
0,
};
/*
* In the legacy file format, the magic number is not used to encode endianness.
* hdr_sz was used to encode endianness. But given that hdr_sz can vary based
* on ABI revisions, we need to try all combinations for all endianness to
* detect the endianness.
*/
static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph)
{
uint64_t ref_size, attr_size;
int i;
for (i = 0 ; attr_file_abi_sizes[i]; i++) {
ref_size = attr_file_abi_sizes[i]
+ sizeof(struct perf_file_section);
if (hdr_sz != ref_size) {
attr_size = bswap_64(hdr_sz);
if (attr_size != ref_size)
continue;
ph->needs_swap = true;
}
pr_debug("ABI%d perf.data file detected, need_swap=%d\n",
i,
ph->needs_swap);
return 0;
}
/* could not determine endianness */
return -1;
}
#define PERF_PIPE_HDR_VER0 16
static const size_t attr_pipe_abi_sizes[] = {
[0] = PERF_PIPE_HDR_VER0,
0,
};
/*
* In the legacy pipe format, there is an implicit assumption that endiannesss
* between host recording the samples, and host parsing the samples is the
* same. This is not always the case given that the pipe output may always be
* redirected into a file and analyzed on a different machine with possibly a
* different endianness and perf_event ABI revsions in the perf tool itself.
*/
static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
{
u64 attr_size;
int i;
for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
if (hdr_sz != attr_pipe_abi_sizes[i]) {
attr_size = bswap_64(hdr_sz);
if (attr_size != hdr_sz)
continue;
ph->needs_swap = true;
}
pr_debug("Pipe ABI%d perf.data file detected\n", i);
return 0;
}
return -1;
}
static int check_magic_endian(u64 magic, uint64_t hdr_sz,
bool is_pipe, struct perf_header *ph)
{
int ret;
/* check for legacy format */
ret = memcmp(magic, __perf_magic1, sizeof(*magic));
ret = memcmp(&magic, __perf_magic1, sizeof(magic));
if (ret == 0) {
pr_debug("legacy perf.data format\n");
if (!header)
return -1;
if (is_pipe)
return try_all_pipe_abis(hdr_sz, ph);
if (header->attr_size != sizeof(struct perf_file_attr)) {
u64 attr_size = bswap_64(header->attr_size);
if (attr_size != sizeof(struct perf_file_attr))
return -1;
ph->needs_swap = true;
}
return 0;
return try_all_file_abis(hdr_sz, ph);
}
/*
* the new magic number serves two purposes:
* - unique number to identify actual perf.data files
* - encode endianness of file
*/
/* check magic number with same endianness */
if (*magic == __perf_magic2)
/* check magic number with one endianness */
if (magic == __perf_magic2)
return 0;
/* check magic number but opposite endianness */
if (*magic != __perf_magic2_sw)
/* check magic number with opposite endianness */
if (magic != __perf_magic2_sw)
return -1;
ph->needs_swap = true;
@@ -1851,8 +1929,11 @@ int perf_file_header__read(struct perf_file_header *header,
if (ret <= 0)
return -1;
if (check_magic_endian(&header->magic, header, ph) < 0)
if (check_magic_endian(header->magic,
header->attr_size, false, ph) < 0) {
pr_debug("magic/endian check failed\n");
return -1;
}
if (ph->needs_swap) {
mem_bswap_64(header, offsetof(struct perf_file_header,
@@ -1939,21 +2020,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
if (ret <= 0)
return -1;
if (check_magic_endian(&header->magic, NULL, ph) < 0)
if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
pr_debug("endian/magic failed\n");
return -1;
}
if (ph->needs_swap)
header->size = bswap_64(header->size);
if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
return -1;
if (header->size != sizeof(*header)) {
u64 size = bswap_64(header->size);
if (size != sizeof(*header))
return -1;
ph->needs_swap = true;
}
return 0;
}
@@ -1973,6 +2050,52 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
return 0;
}
static int read_attr(int fd, struct perf_header *ph,
struct perf_file_attr *f_attr)
{
struct perf_event_attr *attr = &f_attr->attr;
size_t sz, left;
size_t our_sz = sizeof(f_attr->attr);
int ret;
memset(f_attr, 0, sizeof(*f_attr));
/* read minimal guaranteed structure */
ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
if (ret <= 0) {
pr_debug("cannot read %d bytes of header attr\n",
PERF_ATTR_SIZE_VER0);
return -1;
}
/* on file perf_event_attr size */
sz = attr->size;
if (ph->needs_swap)
sz = bswap_32(sz);
if (sz == 0) {
/* assume ABI0 */
sz = PERF_ATTR_SIZE_VER0;
} else if (sz > our_sz) {
pr_debug("file uses a more recent and unsupported ABI"
" (%zu bytes extra)\n", sz - our_sz);
return -1;
}
/* what we have not yet read and that we know about */
left = sz - PERF_ATTR_SIZE_VER0;
if (left) {
void *ptr = attr;
ptr += PERF_ATTR_SIZE_VER0;
ret = readn(fd, ptr, left);
}
/* read perf_file_section, ids are read in caller */
ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
return ret <= 0 ? -1 : 0;
}
int perf_session__read_header(struct perf_session *session, int fd)
{
struct perf_header *header = &session->header;
@@ -1988,19 +2111,17 @@ int perf_session__read_header(struct perf_session *session, int fd)
if (session->fd_pipe)
return perf_header__read_pipe(session, fd);
if (perf_file_header__read(&f_header, header, fd) < 0) {
pr_debug("incompatible file format\n");
if (perf_file_header__read(&f_header, header, fd) < 0)
return -EINVAL;
}
nr_attrs = f_header.attrs.size / sizeof(f_attr);
nr_attrs = f_header.attrs.size / f_header.attr_size;
lseek(fd, f_header.attrs.offset, SEEK_SET);
for (i = 0; i < nr_attrs; i++) {
struct perf_evsel *evsel;
off_t tmp;
if (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
if (read_attr(fd, header, &f_attr) < 0)
goto out_errno;
if (header->needs_swap)

View File

@@ -27,7 +27,7 @@ enum {
HEADER_EVENT_DESC,
HEADER_CPU_TOPOLOGY,
HEADER_NUMA_TOPOLOGY,
HEADER_BRANCH_STACK,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};

View File

@@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists)
hists__set_col_len(hists, col, 0);
}
static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
{
const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
if (hists__col_len(hists, dso) < unresolved_col_width &&
!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
!symbol_conf.dso_list)
hists__set_col_len(hists, dso, unresolved_col_width);
}
static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
{
const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
u16 len;
if (h->ms.sym)
hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
else {
const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
!symbol_conf.dso_list)
hists__set_col_len(hists, HISTC_DSO,
unresolved_col_width);
}
hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
else
hists__set_unres_dso_col_len(hists, HISTC_DSO);
len = thread__comm_len(h->thread);
if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
len = dso__name_len(h->ms.map->dso);
hists__new_col_len(hists, HISTC_DSO, len);
}
if (h->branch_info) {
int symlen;
/*
* +4 accounts for '[x] ' priv level info
* +2 account of 0x prefix on raw addresses
*/
if (h->branch_info->from.sym) {
symlen = (int)h->branch_info->from.sym->namelen + 4;
hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
symlen = dso__name_len(h->branch_info->from.map->dso);
hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
}
if (h->branch_info->to.sym) {
symlen = (int)h->branch_info->to.sym->namelen + 4;
hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
symlen = dso__name_len(h->branch_info->to.map->dso);
hists__new_col_len(hists, HISTC_DSO_TO, symlen);
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
}
}
}
static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent)
return 0;
}
struct hist_entry *__hists__add_entry(struct hists *hists,
static struct hist_entry *add_hist_entry(struct hists *hists,
struct hist_entry *entry,
struct addr_location *al,
struct symbol *sym_parent, u64 period)
u64 period)
{
struct rb_node **p;
struct rb_node *parent = NULL;
struct hist_entry *he;
struct hist_entry entry = {
.thread = al->thread,
.ms = {
.map = al->map,
.sym = al->sym,
},
.cpu = al->cpu,
.ip = al->addr,
.level = al->level,
.period = period,
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
};
int cmp;
pthread_mutex_lock(&hists->lock);
@@ -225,7 +248,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
parent = *p;
he = rb_entry(parent, struct hist_entry, rb_node_in);
cmp = hist_entry__cmp(&entry, he);
cmp = hist_entry__cmp(entry, he);
if (!cmp) {
he->period += period;
@@ -239,7 +262,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
p = &(*p)->rb_right;
}
he = hist_entry__new(&entry);
he = hist_entry__new(entry);
if (!he)
goto out_unlock;
@@ -252,6 +275,51 @@ out_unlock:
return he;
}
struct hist_entry *__hists__add_branch_entry(struct hists *self,
struct addr_location *al,
struct symbol *sym_parent,
struct branch_info *bi,
u64 period)
{
struct hist_entry entry = {
.thread = al->thread,
.ms = {
.map = bi->to.map,
.sym = bi->to.sym,
},
.cpu = al->cpu,
.ip = bi->to.addr,
.level = al->level,
.period = period,
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
.branch_info = bi,
};
return add_hist_entry(self, &entry, al, period);
}
struct hist_entry *__hists__add_entry(struct hists *self,
struct addr_location *al,
struct symbol *sym_parent, u64 period)
{
struct hist_entry entry = {
.thread = al->thread,
.ms = {
.map = al->map,
.sym = al->sym,
},
.cpu = al->cpu,
.ip = al->addr,
.level = al->level,
.period = period,
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
};
return add_hist_entry(self, &entry, al, period);
}
int64_t
hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
{

View File

@@ -42,6 +42,11 @@ enum hist_column {
HISTC_COMM,
HISTC_PARENT,
HISTC_CPU,
HISTC_MISPREDICT,
HISTC_SYMBOL_FROM,
HISTC_SYMBOL_TO,
HISTC_DSO_FROM,
HISTC_DSO_TO,
HISTC_NR_COLS, /* Last entry */
};
@@ -74,6 +79,12 @@ int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
struct hists *hists);
void hist_entry__free(struct hist_entry *);
struct hist_entry *__hists__add_branch_entry(struct hists *self,
struct addr_location *al,
struct symbol *sym_parent,
struct branch_info *bi,
u64 period);
void hists__output_resort(struct hists *self);
void hists__output_resort_threaded(struct hists *hists);
void hists__collapse_resort(struct hists *self);

View File

@@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force)
self->fd = STDIN_FILENO;
if (perf_session__read_header(self, self->fd) < 0)
pr_err("incompatible file format");
pr_err("incompatible file format (rerun with -v to learn more)");
return 0;
}
@@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force)
}
if (perf_session__read_header(self, self->fd) < 0) {
pr_err("incompatible file format");
pr_err("incompatible file format (rerun with -v to learn more)");
goto out_close;
}
@@ -229,6 +229,64 @@ static bool symbol__match_parent_regex(struct symbol *sym)
return 0;
}
static const u8 cpumodes[] = {
PERF_RECORD_MISC_USER,
PERF_RECORD_MISC_KERNEL,
PERF_RECORD_MISC_GUEST_USER,
PERF_RECORD_MISC_GUEST_KERNEL
};
#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
static void ip__resolve_ams(struct machine *self, struct thread *thread,
struct addr_map_symbol *ams,
u64 ip)
{
struct addr_location al;
size_t i;
u8 m;
memset(&al, 0, sizeof(al));
for (i = 0; i < NCPUMODES; i++) {
m = cpumodes[i];
/*
* We cannot use the header.misc hint to determine whether a
* branch stack address is user, kernel, guest, hypervisor.
* Branches may straddle the kernel/user/hypervisor boundaries.
* Thus, we have to try consecutively until we find a match
* or else, the symbol is unknown
*/
thread__find_addr_location(thread, self, m, MAP__FUNCTION,
ip, &al, NULL);
if (al.sym)
goto found;
}
found:
ams->addr = ip;
ams->al_addr = al.addr;
ams->sym = al.sym;
ams->map = al.map;
}
struct branch_info *machine__resolve_bstack(struct machine *self,
struct thread *thr,
struct branch_stack *bs)
{
struct branch_info *bi;
unsigned int i;
bi = calloc(bs->nr, sizeof(struct branch_info));
if (!bi)
return NULL;
for (i = 0; i < bs->nr; i++) {
ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
bi[i].flags = bs->entries[i].flags;
}
return bi;
}
int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
struct thread *thread,
struct ip_callchain *chain,
@@ -697,6 +755,18 @@ static void callchain__printf(struct perf_sample *sample)
i, sample->callchain->ips[i]);
}
static void branch_stack__printf(struct perf_sample *sample)
{
uint64_t i;
printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
for (i = 0; i < sample->branch_stack->nr; i++)
printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
i, sample->branch_stack->entries[i].from,
sample->branch_stack->entries[i].to);
}
static void perf_session__print_tstamp(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample)
@@ -744,6 +814,9 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
callchain__printf(sample);
if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
branch_stack__printf(sample);
}
static struct machine *

View File

@@ -73,6 +73,10 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel
struct ip_callchain *chain,
struct symbol **parent);
struct branch_info *machine__resolve_bstack(struct machine *self,
struct thread *thread,
struct branch_stack *bs);
bool perf_session__has_traces(struct perf_session *self, const char *msg);
void mem_bswap_64(void *src, int byte_size);

View File

@@ -8,6 +8,7 @@ const char default_sort_order[] = "comm,dso,symbol";
const char *sort_order = default_sort_order;
int sort__need_collapse = 0;
int sort__has_parent = 0;
int sort__branch_mode = -1; /* -1 = means not set */
enum sort_type sort__first_dimension;
@@ -94,21 +95,10 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
}
struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
/* --sort dso */
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
{
struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
struct dso *dso_l = map_l ? map_l->dso : NULL;
struct dso *dso_r = map_r ? map_r->dso : NULL;
const char *dso_name_l, *dso_name_r;
if (!dso_l || !dso_r)
@@ -125,18 +115,87 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
return strcmp(dso_name_l, dso_name_r);
}
static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
/* --sort dso */
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (self->ms.map && self->ms.map->dso) {
const char *dso_name = !verbose ? self->ms.map->dso->short_name :
self->ms.map->dso->long_name;
return _sort__dso_cmp(left->ms.map, right->ms.map);
}
static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
u64 ip_l, u64 ip_r)
{
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
if (sym_l == sym_r)
return 0;
if (sym_l)
ip_l = sym_l->start;
if (sym_r)
ip_r = sym_r->start;
return (int64_t)(ip_r - ip_l);
}
static int _hist_entry__dso_snprintf(struct map *map, char *bf,
size_t size, unsigned int width)
{
if (map && map->dso) {
const char *dso_name = !verbose ? map->dso->short_name :
map->dso->long_name;
return repsep_snprintf(bf, size, "%-*s", width, dso_name);
}
return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
}
static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
}
static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
u64 ip, char level, char *bf, size_t size,
unsigned int width __used)
{
size_t ret = 0;
if (verbose) {
char o = map ? dso__symtab_origin(map->dso) : '!';
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
BITS_PER_LONG / 4, ip, o);
}
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
if (sym)
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret,
sym->name);
else {
size_t len = BITS_PER_LONG / 4;
ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
len, ip);
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret, "");
}
return ret;
}
struct sort_entry sort_dso = {
.se_header = "Shared Object",
.se_cmp = sort__dso_cmp,
@@ -144,8 +203,14 @@ struct sort_entry sort_dso = {
.se_width_idx = HISTC_DSO,
};
/* --sort symbol */
static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
self->level, bf, size, width);
}
/* --sort symbol */
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
@@ -163,31 +228,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
ip_l = left->ms.sym->start;
ip_r = right->ms.sym->start;
return (int64_t)(ip_r - ip_l);
}
static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
size_t ret = 0;
if (verbose) {
char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
BITS_PER_LONG / 4, self->ip, o);
}
if (!sort_dso.elide)
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
if (self->ms.sym)
ret += repsep_snprintf(bf + ret, size - ret, "%s",
self->ms.sym->name);
else
ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
BITS_PER_LONG / 4, self->ip);
return ret;
return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
}
struct sort_entry sort_sym = {
@@ -246,19 +287,155 @@ struct sort_entry sort_cpu = {
.se_width_idx = HISTC_CPU,
};
static int64_t
sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->from.map,
right->branch_info->from.map);
}
static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->branch_info->from.map,
bf, size, width);
}
struct sort_entry sort_dso_from = {
.se_header = "Source Shared Object",
.se_cmp = sort__dso_from_cmp,
.se_snprintf = hist_entry__dso_from_snprintf,
.se_width_idx = HISTC_DSO_FROM,
};
static int64_t
sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->to.map,
right->branch_info->to.map);
}
static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->branch_info->to.map,
bf, size, width);
}
static int64_t
sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *from_l = &left->branch_info->from;
struct addr_map_symbol *from_r = &right->branch_info->from;
if (!from_l->sym && !from_r->sym)
return right->level - left->level;
return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
from_r->addr);
}
static int64_t
sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *to_l = &left->branch_info->to;
struct addr_map_symbol *to_r = &right->branch_info->to;
if (!to_l->sym && !to_r->sym)
return right->level - left->level;
return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
}
static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
struct addr_map_symbol *from = &self->branch_info->from;
return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
self->level, bf, size, width);
}
static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
struct addr_map_symbol *to = &self->branch_info->to;
return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
self->level, bf, size, width);
}
struct sort_entry sort_dso_to = {
.se_header = "Target Shared Object",
.se_cmp = sort__dso_to_cmp,
.se_snprintf = hist_entry__dso_to_snprintf,
.se_width_idx = HISTC_DSO_TO,
};
struct sort_entry sort_sym_from = {
.se_header = "Source Symbol",
.se_cmp = sort__sym_from_cmp,
.se_snprintf = hist_entry__sym_from_snprintf,
.se_width_idx = HISTC_SYMBOL_FROM,
};
struct sort_entry sort_sym_to = {
.se_header = "Target Symbol",
.se_cmp = sort__sym_to_cmp,
.se_snprintf = hist_entry__sym_to_snprintf,
.se_width_idx = HISTC_SYMBOL_TO,
};
static int64_t
sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
{
const unsigned char mp = left->branch_info->flags.mispred !=
right->branch_info->flags.mispred;
const unsigned char p = left->branch_info->flags.predicted !=
right->branch_info->flags.predicted;
return mp || p;
}
static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width){
static const char *out = "N/A";
if (self->branch_info->flags.predicted)
out = "N";
else if (self->branch_info->flags.mispred)
out = "Y";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
struct sort_entry sort_mispredict = {
.se_header = "Branch Mispredicted",
.se_cmp = sort__mispredict_cmp,
.se_snprintf = hist_entry__mispredict_snprintf,
.se_width_idx = HISTC_MISPREDICT,
};
struct sort_dimension {
const char *name;
struct sort_entry *entry;
int taken;
};
#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
static struct sort_dimension sort_dimensions[] = {
{ .name = "pid", .entry = &sort_thread, },
{ .name = "comm", .entry = &sort_comm, },
{ .name = "dso", .entry = &sort_dso, },
{ .name = "symbol", .entry = &sort_sym, },
{ .name = "parent", .entry = &sort_parent, },
{ .name = "cpu", .entry = &sort_cpu, },
DIM(SORT_PID, "pid", sort_thread),
DIM(SORT_COMM, "comm", sort_comm),
DIM(SORT_DSO, "dso", sort_dso),
DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
DIM(SORT_SYM, "symbol", sort_sym),
DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
};
int sort_dimension__add(const char *tok)
@@ -270,7 +447,6 @@ int sort_dimension__add(const char *tok)
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sd->entry == &sort_parent) {
int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
if (ret) {
@@ -302,6 +478,16 @@ int sort_dimension__add(const char *tok)
sort__first_dimension = SORT_PARENT;
else if (!strcmp(sd->name, "cpu"))
sort__first_dimension = SORT_CPU;
else if (!strcmp(sd->name, "symbol_from"))
sort__first_dimension = SORT_SYM_FROM;
else if (!strcmp(sd->name, "symbol_to"))
sort__first_dimension = SORT_SYM_TO;
else if (!strcmp(sd->name, "dso_from"))
sort__first_dimension = SORT_DSO_FROM;
else if (!strcmp(sd->name, "dso_to"))
sort__first_dimension = SORT_DSO_TO;
else if (!strcmp(sd->name, "mispredict"))
sort__first_dimension = SORT_MISPREDICT;
}
list_add_tail(&sd->entry->list, &hist_entry__sort_list);
@@ -309,7 +495,6 @@ int sort_dimension__add(const char *tok)
return 0;
}
return -ESRCH;
}

View File

@@ -31,11 +31,16 @@ extern const char *parent_pattern;
extern const char default_sort_order[];
extern int sort__need_collapse;
extern int sort__has_parent;
extern int sort__branch_mode;
extern char *field_sep;
extern struct sort_entry sort_comm;
extern struct sort_entry sort_dso;
extern struct sort_entry sort_sym;
extern struct sort_entry sort_parent;
extern struct sort_entry sort_dso_from;
extern struct sort_entry sort_dso_to;
extern struct sort_entry sort_sym_from;
extern struct sort_entry sort_sym_to;
extern enum sort_type sort__first_dimension;
/**
@@ -72,6 +77,7 @@ struct hist_entry {
struct hist_entry *pair;
struct rb_root sorted_chain;
};
struct branch_info *branch_info;
struct callchain_root callchain[0];
};
@@ -82,6 +88,11 @@ enum sort_type {
SORT_SYM,
SORT_PARENT,
SORT_CPU,
SORT_DSO_FROM,
SORT_DSO_TO,
SORT_SYM_FROM,
SORT_SYM_TO,
SORT_MISPREDICT,
};
/*

View File

@@ -5,6 +5,7 @@
#include <stdbool.h>
#include <stdint.h>
#include "map.h"
#include "../perf.h"
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
@@ -96,7 +97,11 @@ struct symbol_conf {
*col_width_list_str;
struct strlist *dso_list,
*comm_list,
*sym_list;
*sym_list,
*dso_from_list,
*dso_to_list,
*sym_from_list,
*sym_to_list;
const char *symfs;
};
@@ -120,6 +125,19 @@ struct map_symbol {
bool has_children;
};
struct addr_map_symbol {
struct map *map;
struct symbol *sym;
u64 addr;
u64 al_addr;
};
struct branch_info {
struct addr_map_symbol from;
struct addr_map_symbol to;
struct branch_flags flags;
};
struct addr_location {
struct thread *thread;
struct map *map;

View File

@@ -805,8 +805,11 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
self->hists = hists;
self->b.refresh = hist_browser__refresh;
self->b.seek = ui_browser__hists_seek;
self->b.use_navkeypressed = true,
self->has_symbols = sort_sym.list.next != NULL;
self->b.use_navkeypressed = true;
if (sort__branch_mode == 1)
self->has_symbols = sort_sym_from.list.next != NULL;
else
self->has_symbols = sort_sym.list.next != NULL;
}
return self;
@@ -853,6 +856,16 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
return printed;
}
static inline void free_popup_options(char **options, int n)
{
int i;
for (i = 0; i < n; ++i) {
free(options[i]);
options[i] = NULL;
}
}
static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
const char *helpline, const char *ev_name,
bool left_exits,
@@ -861,7 +874,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
{
struct hists *self = &evsel->hists;
struct hist_browser *browser = hist_browser__new(self);
struct branch_info *bi;
struct pstack *fstack;
char *options[16];
int nr_options = 0;
int key = -1;
if (browser == NULL)
@@ -873,13 +889,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
ui_helpline__push(helpline);
memset(options, 0, sizeof(options));
while (1) {
const struct thread *thread = NULL;
const struct dso *dso = NULL;
char *options[16];
int nr_options = 0, choice = 0, i,
int choice = 0,
annotate = -2, zoom_dso = -2, zoom_thread = -2,
browse_map = -2;
annotate_f = -2, annotate_t = -2, browse_map = -2;
nr_options = 0;
key = hist_browser__run(browser, ev_name, timer, arg, delay_secs);
@@ -887,7 +906,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
thread = hist_browser__selected_thread(browser);
dso = browser->selection->map ? browser->selection->map->dso : NULL;
}
switch (key) {
case K_TAB:
case K_UNTAB:
@@ -902,7 +920,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
if (!browser->has_symbols) {
ui_browser__warning(&browser->b, delay_secs * 2,
"Annotation is only available for symbolic views, "
"include \"sym\" in --sort to use it.");
"include \"sym*\" in --sort to use it.");
continue;
}
@@ -972,12 +990,34 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
if (!browser->has_symbols)
goto add_exit_option;
if (browser->selection != NULL &&
browser->selection->sym != NULL &&
!browser->selection->map->dso->annotate_warned &&
asprintf(&options[nr_options], "Annotate %s",
browser->selection->sym->name) > 0)
annotate = nr_options++;
if (sort__branch_mode == 1) {
bi = browser->he_selection->branch_info;
if (browser->selection != NULL &&
bi &&
bi->from.sym != NULL &&
!bi->from.map->dso->annotate_warned &&
asprintf(&options[nr_options], "Annotate %s",
bi->from.sym->name) > 0)
annotate_f = nr_options++;
if (browser->selection != NULL &&
bi &&
bi->to.sym != NULL &&
!bi->to.map->dso->annotate_warned &&
(bi->to.sym != bi->from.sym ||
bi->to.map->dso != bi->from.map->dso) &&
asprintf(&options[nr_options], "Annotate %s",
bi->to.sym->name) > 0)
annotate_t = nr_options++;
} else {
if (browser->selection != NULL &&
browser->selection->sym != NULL &&
!browser->selection->map->dso->annotate_warned &&
asprintf(&options[nr_options], "Annotate %s",
browser->selection->sym->name) > 0)
annotate = nr_options++;
}
if (thread != NULL &&
asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
@@ -998,25 +1038,39 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
browse_map = nr_options++;
add_exit_option:
options[nr_options++] = (char *)"Exit";
retry_popup_menu:
choice = ui__popup_menu(nr_options, options);
for (i = 0; i < nr_options - 1; ++i)
free(options[i]);
if (choice == nr_options - 1)
break;
if (choice == -1)
if (choice == -1) {
free_popup_options(options, nr_options - 1);
continue;
}
if (choice == annotate) {
if (choice == annotate || choice == annotate_t || choice == annotate_f) {
struct hist_entry *he;
int err;
do_annotate:
he = hist_browser__selected_entry(browser);
if (he == NULL)
continue;
/*
* we stash the branch_info symbol + map into the
* the ms so we don't have to rewrite all the annotation
* code to use branch_info.
* in branch mode, the ms struct is not used
*/
if (choice == annotate_f) {
he->ms.sym = he->branch_info->from.sym;
he->ms.map = he->branch_info->from.map;
} else if (choice == annotate_t) {
he->ms.sym = he->branch_info->to.sym;
he->ms.map = he->branch_info->to.map;
}
/*
* Don't let this be freed, say, by hists__decay_entry.
*/
@@ -1024,9 +1078,18 @@ do_annotate:
err = hist_entry__tui_annotate(he, evsel->idx,
timer, arg, delay_secs);
he->used = false;
/*
* offer option to annotate the other branch source or target
* (if they exists) when returning from annotate
*/
if ((err == 'q' || err == CTRL('c'))
&& annotate_t != -2 && annotate_f != -2)
goto retry_popup_menu;
ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
if (err)
ui_browser__handle_resize(&browser->b);
} else if (choice == browse_map)
map__browse(browser->selection->map);
else if (choice == zoom_dso) {
@@ -1072,6 +1135,7 @@ out_free_stack:
pstack__delete(fstack);
out:
hist_browser__delete(browser);
free_popup_options(options, nr_options - 1);
return key;
}