Merge branch 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (24 commits)
  tracing/urgent: warn in case of ftrace_start_up inbalance
  tracing/urgent: fix unbalanced ftrace_start_up
  function-graph: add stack frame test
  function-graph: disable when both x86_32 and optimize for size are configured
  ring-buffer: have benchmark test print to trace buffer
  ring-buffer: do not grab locks in nmi
  ring-buffer: add locks around rb_per_cpu_empty
  ring-buffer: check for less than two in size allocation
  ring-buffer: remove useless compile check for buffer_page size
  ring-buffer: remove useless warn on check
  ring-buffer: use BUF_PAGE_HDR_SIZE in calculating index
  tracing: update sample event documentation
  tracing/filters: fix race between filter setting and module unload
  tracing/filters: free filter_string in destroy_preds()
  ring-buffer: use commit counters for commit pointer accounting
  ring-buffer: remove unused variable
  ring-buffer: have benchmark test handle discarded events
  ring-buffer: prevent adding write in discarded area
  tracing/filters: strloc should be unsigned short
  tracing/filters: operand can be negative
  ...

Fix up kmemcheck-induced conflict in kernel/trace/ring_buffer.c manually

kernel/trace/Kconfig

@@ -18,6 +18,13 @@ config HAVE_FUNCTION_TRACER
 config HAVE_FUNCTION_GRAPH_TRACER
 	bool
 
+config HAVE_FUNCTION_GRAPH_FP_TEST
+	bool
+	help
+	 An arch may pass in a unique value (frame pointer) to both the
+	 entering and exiting of a function. On exit, the value is compared
+	 and if it does not match, then it will panic the kernel.
+
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	bool
 	help
@@ -121,6 +128,7 @@ config FUNCTION_GRAPH_TRACER
 	bool "Kernel Function Graph Tracer"
 	depends on HAVE_FUNCTION_GRAPH_TRACER
 	depends on FUNCTION_TRACER
+	depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
 	default y
 	help
 	  Enable the kernel to trace a function at both its return

kernel/trace/ftrace.c

@@ -1224,6 +1224,13 @@ static void ftrace_shutdown(int command)
 		return;
 
 	ftrace_start_up--;
+	/*
+	 * Just warn in case of unbalance, no need to kill ftrace, it's not
+	 * critical but the ftrace_call callers may be never nopped again after
+	 * further ftrace uses.
+	 */
+	WARN_ON_ONCE(ftrace_start_up < 0);
+
 	if (!ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 

kernel/trace/kmemtrace.c

@@ -186,7 +186,7 @@ static int kmem_trace_init(struct trace_array *tr)
 	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		tracing_reset(tr, cpu);
 
 	kmemtrace_start_probes();

kernel/trace/ring_buffer_benchmark.c

@@ -102,8 +102,10 @@ static enum event_status read_page(int cpu)
 			event = (void *)&rpage->data[i];
 			switch (event->type_len) {
 			case RINGBUF_TYPE_PADDING:
-				/* We don't expect any padding */
-				KILL_TEST();
+				/* failed writes may be discarded events */
+				if (!event->time_delta)
+					KILL_TEST();
+				inc = event->array[0] + 4;
 				break;
 			case RINGBUF_TYPE_TIME_EXTEND:
 				inc = 8;
@@ -119,7 +121,7 @@ static enum event_status read_page(int cpu)
 					KILL_TEST();
 					break;
 				}
-				inc = event->array[0];
+				inc = event->array[0] + 4;
 				break;
 			default:
 				entry = ring_buffer_event_data(event);
@@ -201,7 +203,7 @@ static void ring_buffer_producer(void)
 	 * Hammer the buffer for 10 secs (this may
 	 * make the system stall)
 	 */
-	pr_info("Starting ring buffer hammer\n");
+	trace_printk("Starting ring buffer hammer\n");
 	do_gettimeofday(&start_tv);
 	do {
 		struct ring_buffer_event *event;
@@ -237,7 +239,7 @@ static void ring_buffer_producer(void)
 #endif
 
 	} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
-	pr_info("End ring buffer hammer\n");
+	trace_printk("End ring buffer hammer\n");
 
 	if (consumer) {
 		/* Init both completions here to avoid races */
@@ -260,49 +262,50 @@ static void ring_buffer_producer(void)
 	overruns = ring_buffer_overruns(buffer);
 
 	if (kill_test)
-		pr_info("ERROR!\n");
-	pr_info("Time:     %lld (usecs)\n", time);
-	pr_info("Overruns: %lld\n", overruns);
+		trace_printk("ERROR!\n");
+	trace_printk("Time:     %lld (usecs)\n", time);
+	trace_printk("Overruns: %lld\n", overruns);
 	if (disable_reader)
-		pr_info("Read:     (reader disabled)\n");
+		trace_printk("Read:     (reader disabled)\n");
 	else
-		pr_info("Read:     %ld  (by %s)\n", read,
+		trace_printk("Read:     %ld  (by %s)\n", read,
 			read_events ? "events" : "pages");
-	pr_info("Entries:  %lld\n", entries);
-	pr_info("Total:    %lld\n", entries + overruns + read);
-	pr_info("Missed:   %ld\n", missed);
-	pr_info("Hit:      %ld\n", hit);
+	trace_printk("Entries:  %lld\n", entries);
+	trace_printk("Total:    %lld\n", entries + overruns + read);
+	trace_printk("Missed:   %ld\n", missed);
+	trace_printk("Hit:      %ld\n", hit);
 
 	/* Convert time from usecs to millisecs */
 	do_div(time, USEC_PER_MSEC);
 	if (time)
 		hit /= (long)time;
 	else
-		pr_info("TIME IS ZERO??\n");
+		trace_printk("TIME IS ZERO??\n");
 
-	pr_info("Entries per millisec: %ld\n", hit);
+	trace_printk("Entries per millisec: %ld\n", hit);
 
 	if (hit) {
 		/* Calculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / hit;
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 
 	if (missed) {
 		if (time)
 			missed /= (long)time;
 
-		pr_info("Total iterations per millisec: %ld\n", hit + missed);
+		trace_printk("Total iterations per millisec: %ld\n",
+			     hit + missed);
 
 		/* it is possible that hit + missed will overflow and be zero */
 		if (!(hit + missed)) {
-			pr_info("hit + missed overflowed and totalled zero!\n");
+			trace_printk("hit + missed overflowed and totalled zero!\n");
 			hit--; /* make it non zero */
 		}
 
 		/* Caculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / (hit + missed);
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 }
 
@@ -353,7 +356,7 @@ static int ring_buffer_producer_thread(void *arg)
 
 		ring_buffer_producer();
 
-		pr_info("Sleeping for 10 secs\n");
+		trace_printk("Sleeping for 10 secs\n");
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(HZ * SLEEP_TIME);
 		__set_current_state(TASK_RUNNING);

kernel/trace/trace.c

@@ -2191,11 +2191,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&tracing_cpumask_update_lock);
 	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
 	if (err)
 		goto err_unlock;
 
+	mutex_lock(&tracing_cpumask_update_lock);
+
 	local_irq_disable();
 	__raw_spin_lock(&ftrace_max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -2223,8 +2224,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	return count;
 
 err_unlock:
-	mutex_unlock(&tracing_cpumask_update_lock);
-	free_cpumask_var(tracing_cpumask);
+	free_cpumask_var(tracing_cpumask_new);
 
 	return err;
 }
@@ -3626,7 +3626,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	struct trace_seq *s;
 	unsigned long cnt;
 
-	s = kmalloc(sizeof(*s), GFP_ATOMIC);
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
 		return ENOMEM;
 

kernel/trace/trace_events_filter.c

@@ -27,8 +27,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-static DEFINE_MUTEX(filter_mutex);
-
 enum filter_op_ids
 {
 	OP_OR,
@@ -178,7 +176,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 static int filter_pred_strloc(struct filter_pred *pred, void *event,
 			      int val1, int val2)
 {
-	int str_loc = *(int *)(event + pred->offset);
+	unsigned short str_loc = *(unsigned short *)(event + pred->offset);
 	char *addr = (char *)(event + str_loc);
 	int cmp, match;
 
@@ -294,12 +292,12 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 {
 	struct event_filter *filter = call->filter;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
 	if (filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 }
 
 void print_subsystem_event_filter(struct event_subsystem *system,
@@ -307,12 +305,12 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 {
 	struct event_filter *filter = system->filter;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
 	if (filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 }
 
 static struct ftrace_event_field *
@@ -381,6 +379,7 @@ void destroy_preds(struct ftrace_event_call *call)
 			filter_free_pred(filter->preds[i]);
 	}
 	kfree(filter->preds);
+	kfree(filter->filter_string);
 	kfree(filter);
 	call->filter = NULL;
 }
@@ -433,7 +432,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
 		filter->n_preds = 0;
 	}
 
-	mutex_lock(&event_mutex);
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (!call->define_fields)
 			continue;
@@ -443,7 +441,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
 			remove_filter_string(call->filter);
 		}
 	}
-	mutex_unlock(&event_mutex);
 }
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
@@ -546,6 +543,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	filter_pred_fn_t fn;
 	unsigned long long val;
 	int string_type;
+	int ret;
 
 	pred->fn = filter_pred_none;
 
@@ -581,7 +579,11 @@ static int filter_add_pred(struct filter_parse_state *ps,
 			pred->not = 1;
 		return filter_add_pred_fn(ps, call, pred, fn);
 	} else {
-		if (strict_strtoull(pred->str_val, 0, &val)) {
+		if (field->is_signed)
+			ret = strict_strtoll(pred->str_val, 0, &val);
+		else
+			ret = strict_strtoull(pred->str_val, 0, &val);
+		if (ret) {
 			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
 			return -EINVAL;
 		}
@@ -625,7 +627,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 	filter->preds[filter->n_preds] = pred;
 	filter->n_preds++;
 
-	mutex_lock(&event_mutex);
 	list_for_each_entry(call, &ftrace_events, list) {
 
 		if (!call->define_fields)
@@ -636,14 +637,12 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 
 		err = filter_add_pred(ps, call, pred);
 		if (err) {
-			mutex_unlock(&event_mutex);
 			filter_free_subsystem_preds(system);
 			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
 			goto out;
 		}
 		replace_filter_string(call->filter, filter_string);
 	}
-	mutex_unlock(&event_mutex);
 out:
 	return err;
 }
@@ -1070,12 +1069,12 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 
 	struct filter_parse_state *ps;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
 
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_disable_preds(call);
 		remove_filter_string(call->filter);
-		mutex_unlock(&filter_mutex);
+		mutex_unlock(&event_mutex);
 		return 0;
 	}
 
@@ -1103,7 +1102,7 @@ out:
 	postfix_clear(ps);
 	kfree(ps);
 out_unlock:
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 
 	return err;
 }
@@ -1115,12 +1114,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
 	struct filter_parse_state *ps;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
 
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_free_subsystem_preds(system);
 		remove_filter_string(system->filter);
-		mutex_unlock(&filter_mutex);
+		mutex_unlock(&event_mutex);
 		return 0;
 	}
 
@@ -1148,7 +1147,7 @@ out:
 	postfix_clear(ps);
 	kfree(ps);
 out_unlock:
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 
 	return err;
 }

kernel/trace/trace_functions.c

@@ -193,9 +193,11 @@ static void tracing_start_function_trace(void)
 static void tracing_stop_function_trace(void)
 {
 	ftrace_function_enabled = 0;
-	/* OK if they are not registered */
-	unregister_ftrace_function(&trace_stack_ops);
-	unregister_ftrace_function(&trace_ops);
+
+	if (func_flags.val & TRACE_FUNC_OPT_STACK)
+		unregister_ftrace_function(&trace_stack_ops);
+	else
+		unregister_ftrace_function(&trace_ops);
 }
 
 static int func_set_flag(u32 old_flags, u32 bit, int set)

kernel/trace/trace_functions_graph.c

@@ -57,7 +57,8 @@ static struct tracer_flags tracer_flags = {
 
 /* Add a function return address to the trace stack on thread info.*/
 int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+			 unsigned long frame_pointer)
 {
 	unsigned long long calltime;
 	int index;
@@ -85,6 +86,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
 	current->ret_stack[index].subtime = 0;
+	current->ret_stack[index].fp = frame_pointer;
 	*depth = index;
 
 	return 0;
@@ -92,7 +94,8 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 
 /* Retrieve a function return address to the trace stack on thread info.*/
 static void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
+ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
+			unsigned long frame_pointer)
 {
 	int index;
 
@@ -106,6 +109,31 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 		return;
 	}
 
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+	/*
+	 * The arch may choose to record the frame pointer used
+	 * and check it here to make sure that it is what we expect it
+	 * to be. If gcc does not set the place holder of the return
+	 * address in the frame pointer, and does a copy instead, then
+	 * the function graph trace will fail. This test detects this
+	 * case.
+	 *
+	 * Currently, x86_32 with optimize for size (-Os) makes the latest
+	 * gcc do the above.
+	 */
+	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
+		ftrace_graph_stop();
+		WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
+		     "  from func %pF return to %lx\n",
+		     current->ret_stack[index].fp,
+		     frame_pointer,
+		     (void *)current->ret_stack[index].func,
+		     current->ret_stack[index].ret);
+		*ret = (unsigned long)panic;
+		return;
+	}
+#endif
+
 	*ret = current->ret_stack[index].ret;
 	trace->func = current->ret_stack[index].func;
 	trace->calltime = current->ret_stack[index].calltime;
@@ -117,12 +145,12 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-unsigned long ftrace_return_to_handler(void)
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 {
 	struct ftrace_graph_ret trace;
 	unsigned long ret;
 
-	ftrace_pop_return_trace(&trace, &ret);
+	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
 	barrier();