Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Tooling fixes plus a handful of late arriving tooling changes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf tools: Fix link time error with sample_reg_masks on non x86
  perf build: Fix Intel PT instruction decoder dependency problem
  perf dwarf: Fix potential array out of bounds access
  perf record: Add ability to name registers to record
  perf/x86: Add list of register names
  perf script: Enable printing of interrupted machine state
  perf evlist: Open event on evsel cpus and threads
  bpf tools: New API to get name from a BPF object
  perf tools: Fix build on powerpc broken by pt/bts

tools/lib/bpf/libbpf.c

@@ -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)
 {

tools/lib/bpf/libbpf.h

@@ -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)			\

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/Documentation/perf-script.txt

@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, flags.
+	srcline, period, iregs, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace

tools/perf/arch/sh/util/dwarf-regs.c

@@ -51,5 +51,5 @@ const char *sh_regs_table[SH_MAX_REGS] = {
 /* Return architecture dependent register string (for kprobe-tracer) */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= SH_MAX_REGS) ? sh_regs_table[n] : NULL;
+	return (n < SH_MAX_REGS) ? sh_regs_table[n] : NULL;
 }

tools/perf/arch/sparc/util/dwarf-regs.c

@@ -39,5 +39,5 @@ const char *sparc_regs_table[SPARC_MAX_REGS] = {
  */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
+	return (n < SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
 }

tools/perf/arch/x86/util/Build

@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += tsc.o
 libperf-y += pmu.o
 libperf-y += kvm-stat.o
+libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 

tools/perf/arch/x86/util/dwarf-regs.c

@@ -71,5 +71,5 @@ const char *x86_64_regs_table[X86_64_MAX_REGS] = {
 /* Return architecture dependent register string (for kprobe-tracer) */
 const char *get_arch_regstr(unsigned int n)
 {
-	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
+	return (n < ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
 }

tools/perf/arch/x86/util/perf_regs.c

@@ -0,0 +1,28 @@
+#include "../../perf.h"
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG(AX, PERF_REG_X86_AX),
+	SMPL_REG(BX, PERF_REG_X86_BX),
+	SMPL_REG(CX, PERF_REG_X86_CX),
+	SMPL_REG(DX, PERF_REG_X86_DX),
+	SMPL_REG(SI, PERF_REG_X86_SI),
+	SMPL_REG(DI, PERF_REG_X86_DI),
+	SMPL_REG(BP, PERF_REG_X86_BP),
+	SMPL_REG(SP, PERF_REG_X86_SP),
+	SMPL_REG(IP, PERF_REG_X86_IP),
+	SMPL_REG(FLAGS, PERF_REG_X86_FLAGS),
+	SMPL_REG(CS, PERF_REG_X86_CS),
+	SMPL_REG(SS, PERF_REG_X86_SS),
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+	SMPL_REG(R8, PERF_REG_X86_R8),
+	SMPL_REG(R9, PERF_REG_X86_R9),
+	SMPL_REG(R10, PERF_REG_X86_R10),
+	SMPL_REG(R11, PERF_REG_X86_R11),
+	SMPL_REG(R12, PERF_REG_X86_R12),
+	SMPL_REG(R13, PERF_REG_X86_R13),
+	SMPL_REG(R14, PERF_REG_X86_R14),
+	SMPL_REG(R15, PERF_REG_X86_R15),
+#endif
+	SMPL_REG_END
+};

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>
@@ -279,7 +281,7 @@ 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);
@@ -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/builtin-script.c

@@ -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 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	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...]",

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/tests/llvm.c

@@ -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);

tools/perf/util/Build

@@ -75,13 +75,15 @@ libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
 libperf-$(CONFIG_X86) += tsc.o
+libperf-$(CONFIG_AUXTRACE) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(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/evlist.c

@@ -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;

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/intel-pt-decoder/Build

@@ -4,6 +4,7 @@ inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
 inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
 
 $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c

@@ -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;