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>
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index a5766b4..60bddaf 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -152,6 +152,31 @@
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]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 75d230f..1c49d4e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -638,6 +638,77 @@
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 @@
"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()
};
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 358f401..eec392e 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -222,6 +222,7 @@
unsigned int freq;
unsigned int mmap_pages;
unsigned int user_freq;
+ int branch_stack;
u64 default_interval;
u64 user_interval;
const char *cpu_list;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a1fd1cd..f421f7c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -126,6 +126,10 @@
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;