perf record: Add support for sampling taken branch

This patch adds a new option to enable taken branch stack
sampling, i.e., leverage the PERF_SAMPLE_BRANCH_STACK feature
of perf_events.

There is a new option to active this mode: -b.
It is possible to pass a set of filters to select the type of
branches to sample.

The following filters are available:

 - 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 branch target is in the hypervisor

Filters can be combined by passing a comma separated list
to the option:

$ perf record -b any_call,u -e cycles:u branchy

Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: acme@redhat.com
Cc: robert.richter@amd.com
Cc: ming.m.lin@intel.com
Cc: andi@firstfloor.org
Cc: asharma@fb.com
Cc: vweaver1@eecs.utk.edu
Cc: khandual@linux.vnet.ibm.com
Cc: dsahern@gmail.com
Link: http://lkml.kernel.org/r/1328826068-11713-13-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Roberto Agostino Vitillo 2012-02-09 23:21:02 +01:00 committed by Ingo Molnar
parent b5387528f3
commit bdfebd848f
4 changed files with 104 additions and 0 deletions

View File

@ -152,6 +152,31 @@ 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-stack::
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
+
At least one of any, any_call, any_ret, any_ind must be provided. 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.
Note that taken branch sampling may not be available on all processors.
The various filters must be specified as a comma separated list: -b any_ret,u,k
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]

View File

@ -638,6 +638,77 @@ 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 __used)
{
#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, *p;
int ret = -1;
*mode = 0;
/* 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)
goto error;
*mode |= br->mode;
if (!p)
break;
s = p + 1;
}
ret = 0;
if ((*mode & ~ONLY_PLM) == 0) {
error("need at least one branch type with -b\n");
ret = -1;
}
error:
free(os);
return ret;
}
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@ -727,6 +798,9 @@ 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('b', "branch-stack", &record.opts.branch_stack,
"branch mode mask", "branch stack sampling modes",
parse_branch_stack),
OPT_END()
};

View File

@ -222,6 +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

@ -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;