perf/core improvements and fixes

index 9e4eb8fcd559..d23138c06665 100644
@@ -146,6 +146,9 @@ static void intel_pt_insn_decoder(struct insn *insn,
 		case 4:
 			intel_pt_insn->rel = bswap_32(insn->immediate.value);
 			break;
+		default:
+			intel_pt_insn->rel = 0;
+			break;
 		}
 #else
 		intel_pt_insn->rel = insn->immediate.value;

index 4fa4bc4505f5..4252fc22f78f 100644
@@ -880,15 +880,26 @@ struct bpf_object *bpf_object__open(const char *path)
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz)
+					   size_t obj_buf_sz,
+					   const char *name)
 {
+	char tmp_name[64];
+
 	/* param validation */
 	if (!obj_buf || obj_buf_sz <= 0)
 		return NULL;
 
-	pr_debug("loading object from buffer\n");
+	if (!name) {
+		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
+			 (unsigned long)obj_buf,
+			 (unsigned long)obj_buf_sz);
+		tmp_name[sizeof(tmp_name) - 1] = '\0';
+		name = tmp_name;
+	}
+	pr_debug("loading object '%s' from buffer\n",
+		 name);
 
-	return __bpf_object__open("[buffer]", obj_buf, obj_buf_sz);
+	return __bpf_object__open(name, obj_buf, obj_buf_sz);
 }
 
 int bpf_object__unload(struct bpf_object *obj)

@@ -975,6 +986,14 @@ bpf_object__next(struct bpf_object *prev)
 	return next;
 }
 
+const char *
+bpf_object__get_name(struct bpf_object *obj)
+{
+	if (!obj)
+		return NULL;
+	return obj->path;
+}
+
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {

index ea8adc206b62..f16170c95ffd 100644
@@ -28,12 +28,14 @@ struct bpf_object;
 
 struct bpf_object *bpf_object__open(const char *path);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz);
+					   size_t obj_buf_sz,
+					   const char *name);
 void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
 int bpf_object__load(struct bpf_object *obj);
 int bpf_object__unload(struct bpf_object *obj);
+const char *bpf_object__get_name(struct bpf_object *obj);
 
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\

index a337356fd979..52d55971f66f 100644
@@ -26,7 +26,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
 
-	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz);
+	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
 	if (!obj)
 		return -1;
 	bpf_object__close(obj);

index a660022f2c92..1d14f382f614 100644
@@ -279,7 +279,7 @@ static int record__open(struct record *rec)
 
 	evlist__for_each(evlist, pos) {
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
+		if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
 				if (verbose)
 					ui__warning("%s\n", msg);

index 8d00039d6a20..d51a5200c8af 100644
@@ -1181,6 +1181,10 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 		if (evsel->filter == NULL)
 			continue;
 
+		/*
+		 * filters only work for tracepoint event, which doesn't have cpu limit.
+		 * So evlist and evsel should always be same.
+		 */
 		err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter);
 		if (err) {
 			*err_evsel = evsel;

index 4430340292c0..eb51325e8ad9 100644
@@ -6,6 +6,7 @@
 #include "util/exec_cmd.h"
 #include "util/header.h"
 #include "util/parse-options.h"
+#include "util/perf_regs.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"

@@ -46,6 +47,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
 	PERF_OUTPUT_SRCLINE         = 1U << 12,
 	PERF_OUTPUT_PERIOD          = 1U << 13,
+	PERF_OUTPUT_IREGS	    = 1U << 14,
 };
 
 struct output_option {

@@ -66,6 +68,7 @@ struct output_option {
 	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
 	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 	{.str = "period", .field = PERF_OUTPUT_PERIOD},
+	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 };
 
 /* default set to maintain compatibility with current format */

@@ -255,6 +258,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_PERIOD))
 		return -EINVAL;
 
+	if (PRINT_FIELD(IREGS) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS",
+					PERF_OUTPUT_IREGS))
+		return -EINVAL;
+
 	return 0;
 }
 

@@ -352,6 +360,24 @@ out:
 	return 0;
 }
 
+static void print_sample_iregs(union perf_event *event __maybe_unused,
+			  struct perf_sample *sample,
+			  struct thread *thread __maybe_unused,
+			  struct perf_event_attr *attr)
+{
+	struct regs_dump *regs = &sample->intr_regs;
+	uint64_t mask = attr->sample_regs_intr;
+	unsigned i = 0, r;
+
+	if (!regs)
+		return;
+
+	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs->regs[i++];
+		printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+	}
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)

@@ -525,6 +551,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 				     PERF_MAX_STACK_DEPTH);
 	}
 
+	if (PRINT_FIELD(IREGS))
+		print_sample_iregs(event, sample, thread, attr);
+
 	printf("\n");
 }
 

@@ -1643,7 +1672,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,flags", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",

new file mode 100644
index 000000000000..087c84ef5234
@@ -0,0 +1,30 @@
+#include "../../perf.h"
+#include "../../util/perf_regs.h"
+
+#define REG(n, b) { .name = #n, .mask = 1ULL << (b) }
+#define REG_END { .name = NULL }
+const struct sample_reg sample_reg_masks[] = {
+	REG(AX, PERF_REG_X86_AX),
+	REG(BX, PERF_REG_X86_BX),
+	REG(CX, PERF_REG_X86_CX),
+	REG(DX, PERF_REG_X86_DX),
+	REG(SI, PERF_REG_X86_SI),
+	REG(DI, PERF_REG_X86_DI),
+	REG(BP, PERF_REG_X86_BP),
+	REG(SP, PERF_REG_X86_SP),
+	REG(IP, PERF_REG_X86_IP),
+	REG(FLAGS, PERF_REG_X86_FLAGS),
+	REG(CS, PERF_REG_X86_CS),
+	REG(SS, PERF_REG_X86_SS),
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+	REG(R8, PERF_REG_X86_R8),
+	REG(R9, PERF_REG_X86_R9),
+	REG(R10, PERF_REG_X86_R10),
+	REG(R11, PERF_REG_X86_R11),
+	REG(R12, PERF_REG_X86_R12),
+	REG(R13, PERF_REG_X86_R13),
+	REG(R14, PERF_REG_X86_R14),
+	REG(R15, PERF_REG_X86_R15),
+#endif
+	REG_END
+};

index 980dbf76bc98..92c1fff2153e 100644
@@ -5,6 +5,13 @@
 
 struct regs_dump;
 
+struct sample_reg {
+	const char *name;
+	uint64_t mask;
+};
+
+extern const struct sample_reg sample_reg_masks[];
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 

index 1d14f382f614..142eeb341b29 100644
@@ -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,

index cccb4cf575d3..90129accffbe 100644
@@ -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;

index bac25f41a751..c53f79123b37 100644
@@ -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);
 	}
 

71 lines not on this page · raw message

new file mode 100644
index 000000000000..7d762b188007
@@ -0,0 +1,5 @@
+#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 */