Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Warn if given uprobe event accesses memory on older kernel (Masami Hiramatsu)

  - 'perf record' Documentation fixes (Namhyung Kim)

  - Report unsupported events properly in 'perf stat' (Suzuki K. Poulose)

Infrastructure changes:

  - Avoid FORK after COMM when synthesizing records for pre-existing threads (Arnaldo Carvalho de Melo)

  - Reference count struct thread (Arnaldo Carvalho de Melo)

  - Don't keep the session around in 'perf sched', thread refcounting removes that need (Arnaldo Carvalho de Melo)

  - Initialize cpu set in pthread_attr_setaffinity_np() feature test (Adrian Hunter)

  - Only include tsc file for x86 (David Ahern)

  - Compare JOBS to 0 after grep (David Ahern)

  - Improve feature detection messages (Ingo Molnar)

  - Revert "perf: Remove the extra validity check on nr_pages" (Kan Liang)

  - Remove bias offset to find probe point by address (Masami Hiramatsu)

  - Fix build error on ARCH=i386/x86_64/sparc64 (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/kprobes/core.c

@@ -223,34 +223,56 @@ static unsigned long
 __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+	unsigned long faddr;
 
 	kp = get_kprobe((void *)addr);
-	/* There is no probe, return original address */
-	if (!kp)
+	faddr = ftrace_location(addr);
+	/*
+	 * Addresses inside the ftrace location are refused by
+	 * arch_check_ftrace_location(). Something went terribly wrong
+	 * if such an address is checked here.
+	 */
+	if (WARN_ON(faddr && faddr != addr))
+		return 0UL;
+	/*
+	 * Use the current code if it is not modified by Kprobe
+	 * and it cannot be modified by ftrace.
+	 */
+	if (!kp && !faddr)
 		return addr;
 
 	/*
-	 *  Basically, kp->ainsn.insn has an original instruction.
-	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, __copy_instruction() tweaks the displacement of
-	 *  that instruction. In that case, we can't recover the instruction
-	 *  from the kp->ainsn.insn.
+	 * Basically, kp->ainsn.insn has an original instruction.
+	 * However, RIP-relative instruction can not do single-stepping
+	 * at different place, __copy_instruction() tweaks the displacement of
+	 * that instruction. In that case, we can't recover the instruction
+	 * from the kp->ainsn.insn.
 	 *
-	 *  On the other hand, kp->opcode has a copy of the first byte of
-	 *  the probed instruction, which is overwritten by int3. And
-	 *  the instruction at kp->addr is not modified by kprobes except
-	 *  for the first byte, we can recover the original instruction
-	 *  from it and kp->opcode.
+	 * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+	 * of the first byte of the probed instruction, which is overwritten
+	 * by int3. And the instruction at kp->addr is not modified by kprobes
+	 * except for the first byte, we can recover the original instruction
+	 * from it and kp->opcode.
+	 *
+	 * In case of Kprobes using ftrace, we do not have a copy of
+	 * the original instruction. In fact, the ftrace location might
+	 * be modified at anytime and even could be in an inconsistent state.
+	 * Fortunately, we know that the original code is the ideal 5-byte
+	 * long NOP.
 	 */
-	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	buf[0] = kp->opcode;
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (faddr)
+		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+	else
+		buf[0] = kp->opcode;
 	return (unsigned long)buf;
 }
 
 /*
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr)
 		 * normally used, we just go through if there is no kprobe.
 		 */
 		__addr = recover_probed_instruction(buf, addr);
+		if (!__addr)
+			return 0;
 		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 
@@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src)
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
+	if (!recovered_insn)
+		return 0;
 	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
 	/* Another subsystem puts a breakpoint, failed to recover */

arch/x86/kernel/kprobes/opt.c

@@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr)
 			 */
 			return 0;
 		recovered_insn = recover_probed_instruction(buf, addr);
+		if (!recovered_insn)
+			return 0;
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */

kernel/events/core.c

@@ -4446,7 +4446,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	 * If we have rb pages ensure they're a power-of-two number, so we
 	 * can do bitmasks instead of modulo.
 	 */
-	if (!is_power_of_2(nr_pages))
+	if (nr_pages != 0 && !is_power_of_2(nr_pages))
 		return -EINVAL;
 
 	if (vma_size != PAGE_SIZE * (1 + nr_pages))

tools/perf/.gitignore

@@ -1,6 +1,7 @@
 PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
+PERF-FEATURES
 perf
 perf-read-vdso32
 perf-read-vdsox32

tools/perf/Documentation/perf-record.txt

@@ -55,16 +55,18 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
+	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
+	  Each event is separated by commas and the group should be quoted to
+	  prevent the shell interpretation.  You also need to use --group on
+	  "perf report" to view group events together.
+
 --filter=<filter>::
         Event filter.
 
 -a::
 --all-cpus::
         System-wide collection from all CPUs.
 
--l::
-        Scale counter values.
-
 -p::
 --pid=::
 	Record events on existing process ID (comma separated list).
@@ -107,6 +109,10 @@ OPTIONS
 	specification with appended unit character - B/K/M/G. The
 	size is rounded up to have nearest pages power of two value.
 
+--group::
+	Put all events in a single event group.  This precedes the --event
+	option and remains only for backward compatibility.  See --event.
+
 -g::
 	Enables call-graph (stack chain/backtrace) recording.
 

tools/perf/Makefile

@@ -25,7 +25,7 @@ unexport MAKEFLAGS
 #
 ifeq ($(JOBS),)
   JOBS := $(shell grep -c ^processor /proc/cpuinfo 2>/dev/null)
-  ifeq ($(JOBS),)
+  ifeq ($(JOBS),0)
     JOBS := 1
   endif
 endif

tools/perf/bench/mem-memcpy.c

@@ -289,7 +289,7 @@ static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);
@@ -312,7 +312,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
 	void *src = NULL, *dst = NULL;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);

tools/perf/builtin-sched.c

@@ -831,7 +831,7 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
 		return -1;
 	}
 
-	atoms->thread = thread;
+	atoms->thread = thread__get(thread);
 	INIT_LIST_HEAD(&atoms->work_list);
 	__thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid);
 	return 0;
@@ -1439,8 +1439,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	return err;
 }
 
-static int perf_sched__read_events(struct perf_sched *sched,
-				   struct perf_session **psession)
+static int perf_sched__read_events(struct perf_sched *sched)
 {
 	const struct perf_evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",	      process_sched_switch_event, },
@@ -1454,6 +1453,7 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		.path = input_name,
 		.mode = PERF_DATA_MODE_READ,
 	};
+	int rc = -1;
 
 	session = perf_session__new(&file, false, &sched->tool);
 	if (session == NULL) {
@@ -1478,16 +1478,10 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST];
 	}
 
-	if (psession)
-		*psession = session;
-	else
-		perf_session__delete(session);
-
-	return 0;
-
+	rc = 0;
 out_delete:
 	perf_session__delete(session);
-	return -1;
+	return rc;
 }
 
 static void print_bad_events(struct perf_sched *sched)
@@ -1515,12 +1509,10 @@ static void print_bad_events(struct perf_sched *sched)
 static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
-	struct perf_session *session;
 
 	setup_pager();
 
-	/* save session -- references to threads are held in work_list */
-	if (perf_sched__read_events(sched, &session))
+	if (perf_sched__read_events(sched))
 		return -1;
 
 	perf_sched__sort_lat(sched);
@@ -1537,6 +1529,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 		work_list = rb_entry(next, struct work_atoms, node);
 		output_lat_thread(sched, work_list);
 		next = rb_next(next);
+		thread__zput(work_list->thread);
 	}
 
 	printf(" -----------------------------------------------------------------------------------------------------------------\n");
@@ -1548,7 +1541,6 @@ static int perf_sched__lat(struct perf_sched *sched)
 	print_bad_events(sched);
 	printf("\n");
 
-	perf_session__delete(session);
 	return 0;
 }
 
@@ -1557,7 +1549,7 @@ static int perf_sched__map(struct perf_sched *sched)
 	sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
 	setup_pager();
-	if (perf_sched__read_events(sched, NULL))
+	if (perf_sched__read_events(sched))
 		return -1;
 	print_bad_events(sched);
 	return 0;
@@ -1572,7 +1564,7 @@ static int perf_sched__replay(struct perf_sched *sched)
 
 	test_calibrations(sched);
 
-	if (perf_sched__read_events(sched, NULL))
+	if (perf_sched__read_events(sched))
 		return -1;
 
 	printf("nr_run_events:        %ld\n", sched->nr_run_events);

tools/perf/builtin-stat.c

@@ -510,6 +510,9 @@ static int read_counter(struct perf_evsel *counter)
 	int ncpus = perf_evsel__nr_cpus(counter);
 	int cpu, thread;
 
+	if (!counter->supported)
+		return -ENOENT;
+
 	if (counter->system_wide)
 		nthreads = 1;
 
@@ -1285,7 +1288,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	if (prefix)
 		fprintf(output, "%s", prefix);
 
-	if (scaled == -1) {
+	if (scaled == -1 || !counter->supported) {
 		fprintf(output, "%*s%s",
 			csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,

tools/perf/builtin-trace.c

@@ -1741,7 +1741,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	} else
 		ttrace->entry_pending = true;
 
-	trace->current = thread;
+	if (trace->current != thread) {
+		thread__put(trace->current);
+		trace->current = thread__get(thread);
+	}
 
 	return 0;
 }
@@ -2274,6 +2277,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	}
 
 out_disable:
+	thread__zput(trace->current);
+
 	perf_evlist__disable(evlist);
 
 	if (!err) {

tools/perf/config/Makefile

@@ -531,7 +531,7 @@ else
   ifneq ($(feature-libperl), 1)
     CFLAGS += -DNO_LIBPERL
     NO_LIBPERL := 1
-    msg := $(warning Missing perl devel files. Disabling perl scripting support, consider installing perl-ExtUtils-Embed);
+    msg := $(warning Missing perl devel files. Disabling perl scripting support, please install perl-ExtUtils-Embed/libperl-dev);
   else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
@@ -548,22 +548,21 @@ endif
 disable-python = $(eval $(disable-python_code))
 define disable-python_code
   CFLAGS += -DNO_LIBPYTHON
-  $(if $(1),$(warning No $(1) was found))
-  $(warning Python support will not be built)
+  $(warning $1)
   NO_LIBPYTHON := 1
 endef
 
 ifdef NO_LIBPYTHON
-  $(call disable-python)
+  $(call disable-python,Python support disabled by user)
 else
 
   ifndef PYTHON
-    $(call disable-python,python interpreter)
+    $(call disable-python,No python interpreter was found: disables Python support - please install python-devel/python-dev)
   else
     PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
     ifndef PYTHON_CONFIG
-      $(call disable-python,python-config tool)
+      $(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev)
     else
 
       PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
@@ -575,7 +574,7 @@ else
       FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
       ifneq ($(feature-libpython), 1)
-        $(call disable-python,Python.h (for Python 2.x))
+        $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev)
       else
 
         ifneq ($(feature-libpython-version), 1)
@@ -636,7 +635,7 @@ else
             EXTLIBS += -liberty
             CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
           else
-            msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+            msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling)
             CFLAGS += -DNO_DEMANGLE
           endif
         endif
@@ -707,7 +706,7 @@ endif
 
 ifndef NO_LIBBABELTRACE
   ifeq ($(feature-libbabeltrace), 0)
-    msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-devel/libbabeltrace-ctf-dev);
+    msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev);
     NO_LIBBABELTRACE := 1
   else
     CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS)