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

…inux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf tools: Fix time function double declaration with glibc
  perf tools: Fix build by checking if extra warnings are supported
  perf tools: Fix build when using gcc 3.4.6
  perf tools: Add missing header, fixes build
  perf tools: Fix 64 bit integer format strings
  perf test: Fix build on older glibcs
  perf: perf_event_exit_task_context: s/rcu_dereference/rcu_dereference_raw/
  perf test: Use cpu_map->[cpu] when setting affinity
  perf symbols: Fix annotation of thumb code
  perf: Annotate cpuctx->ctx.mutex to avoid a lockdep splat
  powerpc, perf: Fix frequency calculation for overflowing counters (FSL version)
  perf: Fix perf_event_init_task()/perf_event_free_task() interaction
  perf: Fix find_get_context() vs perf_event_exit_task() race

arch/powerpc/kernel/perf_event_fsl_emb.c

@@ -596,6 +596,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			if (left <= 0)
 				left = period;
 			record = 1;
+			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
 			val = 0x80000000LL - left;

kernel/perf_event.c

@@ -2201,13 +2201,6 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/*
-	 * Can't attach events to a dying task.
-	 */
-	err = -ESRCH;
-	if (task->flags & PF_EXITING)
-		goto errout;
-
 	/* Reuse ptrace permission checks for now. */
 	err = -EACCES;
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
@@ -2268,14 +2261,27 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 
 		get_ctx(ctx);
 
-		if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
-			/*
-			 * We raced with some other task; use
-			 * the context they set.
-			 */
+		err = 0;
+		mutex_lock(&task->perf_event_mutex);
+		/*
+		 * If it has already passed perf_event_exit_task().
+		 * we must see PF_EXITING, it takes this mutex too.
+		 */
+		if (task->flags & PF_EXITING)
+			err = -ESRCH;
+		else if (task->perf_event_ctxp[ctxn])
+			err = -EAGAIN;
+		else
+			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		mutex_unlock(&task->perf_event_mutex);
+
+		if (unlikely(err)) {
 			put_task_struct(task);
 			kfree(ctx);
-			goto retry;
+
+			if (err == -EAGAIN)
+				goto retry;
+			goto errout;
 		}
 	}
 
@@ -5374,6 +5380,8 @@ static int pmu_dev_alloc(struct pmu *pmu)
 	goto out;
 }
 
+static struct lock_class_key cpuctx_mutex;
+
 int perf_pmu_register(struct pmu *pmu, char *name, int type)
 {
 	int cpu, ret;
@@ -5422,6 +5430,7 @@ int perf_pmu_register(struct pmu *pmu, char *name, int type)
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		__perf_event_init_context(&cpuctx->ctx);
+		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
@@ -6127,7 +6136,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 * scheduled, so we are now safe from rescheduling changing
 	 * our context.
 	 */
-	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
 	task_ctx_sched_out(child_ctx, EVENT_ALL);
 
 	/*
@@ -6440,11 +6449,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	unsigned long flags;
 	int ret = 0;
 
-	child->perf_event_ctxp[ctxn] = NULL;
-
-	mutex_init(&child->perf_event_mutex);
-	INIT_LIST_HEAD(&child->perf_event_list);
-
 	if (likely(!parent->perf_event_ctxp[ctxn]))
 		return 0;
 
@@ -6533,6 +6537,10 @@ int perf_event_init_task(struct task_struct *child)
 {
 	int ctxn, ret;
 
+	memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
+	mutex_init(&child->perf_event_mutex);
+	INIT_LIST_HEAD(&child->perf_event_list);
+
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
 		if (ret)

tools/perf/Makefile

@@ -204,13 +204,11 @@ EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wshadow
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Winit-self
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wpacked
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wredundant-decls
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstack-protector
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-aliasing=3
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-default
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-enum
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wno-system-headers
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wundef
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wvolatile-register-var
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wwrite-strings
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wbad-function-cast
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-declarations
@@ -294,6 +292,13 @@ ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
 	CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
 
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wstack-protector),y)
+       CFLAGS := $(CFLAGS) -Wstack-protector
+endif
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y)
+       CFLAGS := $(CFLAGS) -Wvolatile-register-var
+endif
 
 ### --- END CONFIGURATION SECTION ---
 

tools/perf/builtin-annotate.c

@@ -212,7 +212,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename)
 			continue;
 
 		offset = start + i;
-		sprintf(cmd, "addr2line -e %s %016llx", filename, offset);
+		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
 		fp = popen(cmd, "r");
 		if (!fp)
 			continue;
@@ -270,9 +270,9 @@ static void hist_entry__print_hits(struct hist_entry *self)
 
 	for (offset = 0; offset < len; ++offset)
 		if (h->ip[offset] != 0)
-			printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
+			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
 			       sym->start + offset, h->ip[offset]);
-	printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
 static int hist_entry__tty_annotate(struct hist_entry *he)

tools/perf/builtin-kmem.c

@@ -371,10 +371,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			addr = data->ptr;
 
 		if (sym != NULL)
-			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
+			snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
 				 addr - map->unmap_ip(map, sym->start));
 		else
-			snprintf(buf, sizeof(buf), "%#Lx", addr);
+			snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
 		printf(" %-34s |", buf);
 
 		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",

tools/perf/builtin-lock.c

@@ -782,9 +782,9 @@ static void print_result(void)
 		pr_info("%10u ", st->nr_acquired);
 		pr_info("%10u ", st->nr_contended);
 
-		pr_info("%15llu ", st->wait_time_total);
-		pr_info("%15llu ", st->wait_time_max);
-		pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ?
+		pr_info("%15" PRIu64 " ", st->wait_time_total);
+		pr_info("%15" PRIu64 " ", st->wait_time_max);
+		pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ?
 		       0 : st->wait_time_min);
 		pr_info("\n");
 	}

tools/perf/builtin-record.c

@@ -817,7 +817,7 @@ static int __cmd_record(int argc, const char **argv)
 	 * Approximate RIP event size: 24 bytes.
 	 */
 	fprintf(stderr,
-		"[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n",
+		"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
 		(double)bytes_written / 1024.0 / 1024.0,
 		output_name,
 		bytes_written / 24);

tools/perf/builtin-report.c

@@ -197,7 +197,7 @@ static int process_read_event(event_t *event, struct sample_data *sample __used,
 					   event->read.value);
 	}
 
-	dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid,
+	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
 		    attr ? __event_name(attr->type, attr->config) : "FAIL",
 		    event->read.value);
 

tools/perf/builtin-sched.c

@@ -193,7 +193,7 @@ static void calibrate_run_measurement_overhead(void)
 	}
 	run_measurement_overhead = min_delta;
 
-	printf("run measurement overhead: %Ld nsecs\n", min_delta);
+	printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static void calibrate_sleep_measurement_overhead(void)
@@ -211,7 +211,7 @@ static void calibrate_sleep_measurement_overhead(void)
 	min_delta -= 10000;
 	sleep_measurement_overhead = min_delta;
 
-	printf("sleep measurement overhead: %Ld nsecs\n", min_delta);
+	printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static struct sched_atom *
@@ -617,13 +617,13 @@ static void test_calibrations(void)
 	burn_nsecs(1e6);
 	T1 = get_nsecs();
 
-	printf("the run test took %Ld nsecs\n", T1-T0);
+	printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
 
 	T0 = get_nsecs();
 	sleep_nsecs(1e6);
 	T1 = get_nsecs();
 
-	printf("the sleep test took %Ld nsecs\n", T1-T0);
+	printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
 }
 
 #define FILL_FIELD(ptr, field, event, data)	\
@@ -816,10 +816,10 @@ replay_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 	if (verbose) {
-		printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n",
+		printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
 			switch_event->prev_comm, switch_event->prev_pid,
 			switch_event->next_comm, switch_event->next_pid,
 			delta);
@@ -1048,7 +1048,7 @@ latency_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
 	sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1221,7 +1221,7 @@ static void output_lat_thread(struct work_atoms *work_list)
 
 	avg = work_list->total_lat / work_list->nb_atoms;
 
-	printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
 	      (double)work_list->total_runtime / 1e6,
 		 work_list->nb_atoms, (double)avg / 1e6,
 		 (double)work_list->max_lat / 1e6,
@@ -1423,7 +1423,7 @@ map_switch_event(struct trace_switch_event *switch_event,
 		delta = 0;
 
 	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
+		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
 	sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1713,7 +1713,7 @@ static void __cmd_lat(void)
 	}
 
 	printf(" -----------------------------------------------------------------------------------------\n");
-	printf("  TOTAL:                |%11.3f ms |%9Ld |\n",
+	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
 		(double)all_runtime/1e6, all_count);
 
 	printf(" ---------------------------------------------------\n");

tools/perf/builtin-script.c

@@ -77,8 +77,8 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 	if (session->sample_type & PERF_SAMPLE_RAW) {
 		if (debug_mode) {
 			if (sample->time < last_timestamp) {
-				pr_err("Samples misordered, previous: %llu "
-					"this: %llu\n", last_timestamp,
+				pr_err("Samples misordered, previous: %" PRIu64
+					" this: %" PRIu64 "\n", last_timestamp,
 					sample->time);
 				nr_unordered++;
 			}
@@ -126,7 +126,7 @@ static int __cmd_script(struct perf_session *session)
 	ret = perf_session__process_events(session, &event_ops);
 
 	if (debug_mode)
-		pr_err("Misordered timestamps: %llu\n", nr_unordered);
+		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
 	return ret;
 }

tools/perf/builtin-stat.c

@@ -206,8 +206,8 @@ static int read_counter_aggr(struct perf_evsel *counter)
 		update_stats(&ps->res_stats[i], count[i]);
 
 	if (verbose) {
-		fprintf(stderr, "%s: %Ld %Ld %Ld\n", event_name(counter),
-				count[0], count[1], count[2]);
+		fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+			event_name(counter), count[0], count[1], count[2]);
 	}
 
 	/*