perf record: Add ability to name registers to record

This patch modifies the -I/--int-regs option to enablepassing the name
of the registers to sample on interrupt. Registers can be specified by
their symbolic names. For instance on x86, --intr-regs=ax,si.

The motivation is to reduce the size of the perf.data file and the
overhead of sampling by only collecting the registers useful to a
specific analysis. For instance, for value profiling, sampling only the
registers used to passed arguements to functions.

With no parameter, the --intr-regs still records all possible registers
based on the architecture.

To name registers, it is necessary to use the long form of the option,
i.e., --intr-regs:

  $ perf record --intr-regs=si,di,r8,r9 .....

To record any possible registers:

  $ perf record -I .....
  $ perf report --intr-regs ...

To display the register, one can use perf report -D

To list the available registers:

  $ perf record --intr-regs=\?
  available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15
Signed-off-by: Stephane Eranian <eranian@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1441039273-16260-4-git-send-email-eranian@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-record.txt

@@ -276,7 +276,11 @@ filter out the startup phase of the program, which is often very different.
 --intr-regs::
 Capture machine state (registers) at interrupt, i.e., on counter overflows for
 each sample. List of captured registers depends on the architecture. This option
-is off by default.
+is off by default. It is possible to select the registers to sample using their
+symbolic names, e.g. on x86, ax, si. To list the available registers use
+--intr-regs=\?. To name registers, pass a comma separated list such as
+--intr-regs=ax,bx. The list of register is architecture dependent.
+
 
 --running-time::
 Record running and enabled time for read events (:S)

tools/perf/builtin-record.c

@@ -27,8 +27,10 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
+#include "util/perf_regs.h"
 #include "util/auxtrace.h"
 #include "util/parse-branch-options.h"
+#include "util/parse-regs-options.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -1080,8 +1082,9 @@ struct option __record_options[] = {
 		    "sample transaction flags (special events only)"),
 	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
 		    "use per-thread mmaps"),
-	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
-		    "Sample machine registers on interrupt"),
+	OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
+		    "sample selected machine registers on interrupt,"
+		    " use -I ? to list register names", parse_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
 	OPT_CALLBACK('k', "clockid", &record.opts,

tools/perf/perf.h

@@ -54,7 +54,6 @@ struct record_opts {
 	bool	     sample_time_set;
 	bool	     callgraph_set;
 	bool	     period;
-	bool	     sample_intr_regs;
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
@@ -64,6 +63,7 @@ struct record_opts {
 	unsigned int auxtrace_mmap_pages;
 	unsigned int user_freq;
 	u64          branch_stack;
+	u64	     sample_intr_regs;
 	u64	     default_interval;
 	u64	     user_interval;
 	size_t	     auxtrace_snapshot_size;

tools/perf/util/Build

@@ -83,6 +83,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
+libperf-y += parse-regs-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o

tools/perf/util/evsel.c

@@ -787,7 +787,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__config_callgraph(evsel, opts, &callchain_param);
 
 	if (opts->sample_intr_regs) {
-		attr->sample_regs_intr = PERF_REGS_MASK;
+		attr->sample_regs_intr = opts->sample_intr_regs;
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 

tools/perf/util/parse-regs-options.c

+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-regs-options.h"
+
+int
+parse_regs(const struct option *opt, const char *str, int unset)
+{
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct sample_reg *r;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -I */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			if (!strcmp(s, "?")) {
+				fprintf(stderr, "available registers: ");
+				for (r = sample_reg_masks; r->name; r++) {
+					fprintf(stderr, "%s ", r->name);
+				}
+				fputc('\n', stderr);
+				/* just printing available regs */
+				return -1;
+			}
+			for (r = sample_reg_masks; r->name; r++) {
+				if (!strcasecmp(s, r->name))
+					break;
+			}
+			if (!r->name) {
+				ui__warning("unknown register %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= r->mask;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to all possible regs */
+	if (*mode == 0)
+		*mode = PERF_REGS_MASK;
+error:
+	free(os);
+	return ret;
+}

tools/perf/util/parse-regs-options.h

+#ifndef _PERF_PARSE_REGS_OPTIONS_H
+#define _PERF_PARSE_REGS_OPTIONS_H 1
+struct option;
+int parse_regs(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_REGS_OPTIONS_H */