Merge commit 'v2.6.32-rc5' into perf/probes

Conflicts:
	kernel/trace/trace_event_profile.c

Merge reason: update to -rc5 and resolve conflict.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/trace/blktrace.c

@@ -855,6 +855,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 			sizeof(r), &r);
 }
 
+/**
+ * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @q:		queue the io is for
+ * @rq:		the source request
+ * @dev:	target device
+ * @from:	source sector
+ *
+ * Description:
+ *     Device mapper remaps request to other devices.
+ *     Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_rq_remap(struct request_queue *q,
+				   struct request *rq, dev_t dev,
+				   sector_t from)
+{
+	struct blk_trace *bt = q->blk_trace;
+	struct blk_io_trace_remap r;
+
+	if (likely(!bt))
+		return;
+
+	r.device_from = cpu_to_be32(dev);
+	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
+	r.sector_from = cpu_to_be64(from);
+
+	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+			rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+			sizeof(r), &r);
+}
+
 /**
  * blk_add_driver_data - Add binary message with driver-specific data
  * @q:		queue the io is for
@@ -922,10 +953,13 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_remap(blk_add_trace_remap);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+	WARN_ON(ret);
 }
 
 static void blk_unregister_tracepoints(void)
 {
+	unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
 	unregister_trace_block_remap(blk_add_trace_remap);
 	unregister_trace_block_split(blk_add_trace_split);
 	unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
@@ -1657,6 +1691,11 @@ int blk_trace_init_sysfs(struct device *dev)
 	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
 }
 
+void blk_trace_remove_sysfs(struct device *dev)
+{
+	sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
+}
+
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING

kernel/trace/ftrace.c

@@ -225,7 +225,11 @@ static void ftrace_update_pid_func(void)
 	if (ftrace_trace_function == ftrace_stub)
 		return;
 
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	func = ftrace_trace_function;
+#else
+	func = __ftrace_trace_function;
+#endif
 
 	if (ftrace_pid_trace) {
 		set_ftrace_pid_function(func);
@@ -1074,14 +1078,9 @@ static void ftrace_replace_code(int enable)
 		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
 			rec->flags |= FTRACE_FL_FAILED;
-			if ((system_state == SYSTEM_BOOTING) ||
-			    !core_kernel_text(rec->ip)) {
-				ftrace_free_rec(rec);
-				} else {
-				ftrace_bug(failed, rec->ip);
-					/* Stop processing */
-					return;
-				}
+			ftrace_bug(failed, rec->ip);
+			/* Stop processing */
+			return;
 		}
 	} while_for_each_ftrace_rec();
 }
@@ -1621,8 +1620,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = iter;
-		} else
+		} else {
+			trace_parser_put(&iter->parser);
 			kfree(iter);
+		}
 	} else
 		file->private_data = iter;
 	mutex_unlock(&ftrace_regex_lock);
@@ -2202,7 +2203,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	struct trace_parser *parser;
 	ssize_t ret, read;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	mutex_lock(&ftrace_regex_lock);
@@ -2216,7 +2217,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	parser = &iter->parser;
 	read = trace_get_user(parser, ubuf, cnt, ppos);
 
-	if (trace_parser_loaded(parser) &&
+	if (read >= 0 && trace_parser_loaded(parser) &&
 	    !trace_parser_cont(parser)) {
 		ret = ftrace_process_regex(parser->buffer,
 					   parser->idx, enable);
@@ -2552,8 +2553,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_parser parser;
-	size_t read = 0;
-	ssize_t ret;
+	ssize_t read, ret;
 
 	if (!cnt || cnt < 0)
 		return 0;
@@ -2562,29 +2562,31 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 
 	if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
 		ret = -EBUSY;
-		goto out;
+		goto out_unlock;
 	}
 
 	if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_unlock;
 	}
 
 	read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-	if (trace_parser_loaded((&parser))) {
+	if (read >= 0 && trace_parser_loaded((&parser))) {
 		parser.buffer[parser.idx] = 0;
 
 		/* we allow only one expression at a time */
 		ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
 					parser.buffer);
 		if (ret)
-			goto out;
+			goto out_free;
 	}
 
 	ret = read;
- out:
+
+out_free:
 	trace_parser_put(&parser);
+out_unlock:
 	mutex_unlock(&graph_lock);
 
 	return ret;
@@ -2655,19 +2657,17 @@ static int ftrace_convert_nops(struct module *mod,
 }
 
 #ifdef CONFIG_MODULES
-void ftrace_release(void *start, void *end)
+void ftrace_release_mod(struct module *mod)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
-	unsigned long s = (unsigned long)start;
-	unsigned long e = (unsigned long)end;
 
-	if (ftrace_disabled || !start || start == end)
+	if (ftrace_disabled)
 		return;
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e)) {
+		if (within_module_core(rec->ip, mod)) {
 			/*
 			 * rec->ip is changed in ftrace_free_rec()
 			 * It should not between s and e if record was freed.
@@ -2699,9 +2699,7 @@ static int ftrace_module_notify(struct notifier_block *self,
 				   mod->num_ftrace_callsites);
 		break;
 	case MODULE_STATE_GOING:
-		ftrace_release(mod->ftrace_callsites,
-			       mod->ftrace_callsites +
-			       mod->num_ftrace_callsites);
+		ftrace_release_mod(mod);
 		break;
 	}
 
@@ -3015,7 +3013,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     struct file *file, void __user *buffer, size_t *lenp,
+		     void __user *buffer, size_t *lenp,
 		     loff_t *ppos)
 {
 	int ret;
@@ -3025,7 +3023,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 	mutex_lock(&ftrace_lock);
 
-	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
+	ret  = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
 		goto out;

kernel/trace/kmemtrace.c

@@ -501,7 +501,7 @@ static int __init init_kmem_tracer(void)
 		return 1;
 	}
 
-	if (!register_tracer(&kmem_tracer)) {
+	if (register_tracer(&kmem_tracer) != 0) {
 		pr_warning("Warning: could not register the kmem tracer\n");
 		return 1;
 	}

kernel/trace/trace.c

@@ -415,7 +415,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 
 	/* read the non-space input */
 	while (cnt && !isspace(ch)) {
-		if (parser->idx < parser->size)
+		if (parser->idx < parser->size - 1)
 			parser->buffer[parser->idx++] = ch;
 		else {
 			ret = -EINVAL;
@@ -1393,7 +1393,7 @@ int trace_array_vprintk(struct trace_array *tr,
 
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	return trace_array_printk(&global_trace, ip, fmt, args);
+	return trace_array_vprintk(&global_trace, ip, fmt, args);
 }
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
@@ -1984,11 +1984,9 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (current_trace)
 		*iter->trace = *current_trace;
 
-	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	cpumask_clear(iter->started);
-
 	if (current_trace && current_trace->print_max)
 		iter->tr = &max_tr;
 	else
@@ -4389,7 +4387,7 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
 		goto out_free_tracing_cpumask;
 
 	/* To save memory, keep the ring buffer size to its minimum */
@@ -4400,7 +4398,6 @@ __init static int tracer_alloc_buffers(void)
 
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
-	cpumask_clear(tracing_reader_cpumask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	global_trace.buffer = ring_buffer_alloc(ring_buf_size,

kernel/trace/trace_branch.c

@@ -34,6 +34,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	struct trace_array *tr = branch_tracer;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
+	struct ring_buffer *buffer;
 	unsigned long flags;
 	int cpu, pc;
 	const char *p;
@@ -54,7 +55,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 		goto out;
 
 	pc = preempt_count();
-	event = trace_buffer_lock_reserve(tr, TRACE_BRANCH,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		goto out;
@@ -74,8 +76,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);

kernel/trace/trace_event_profile.c

@@ -31,7 +31,7 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 	if (atomic_inc_return(&event->profile_count))
 		return 0;
 
-	if (!total_profile_count++) {
+	if (!total_profile_count) {
 		buf = (char *)alloc_percpu(profile_buf_t);
 		if (!buf)
 			goto fail_buf;
@@ -46,14 +46,19 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 	}
 
 	ret = event->profile_enable(event);
-	if (!ret)
+	if (!ret) {
+		total_profile_count++;
 		return 0;
+	}
 
-	kfree(trace_profile_buf_nmi);
 fail_buf_nmi:
-	kfree(trace_profile_buf);
+	if (!total_profile_count) {
+		free_percpu(trace_profile_buf_nmi);
+		free_percpu(trace_profile_buf);
+		trace_profile_buf_nmi = NULL;
+		trace_profile_buf = NULL;
+	}
 fail_buf:
-	total_profile_count--;
 	atomic_dec(&event->profile_count);
 
 	return ret;

kernel/trace/trace_events.c

@@ -228,10 +228,9 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_parser parser;
-	size_t read = 0;
-	ssize_t ret;
+	ssize_t read, ret;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	ret = tracing_update_buffers();
@@ -243,7 +242,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 
 	read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-	if (trace_parser_loaded((&parser))) {
+	if (read >= 0 && trace_parser_loaded((&parser))) {
 		int set = 1;
 
 		if (*parser.buffer == '!')

kernel/trace/trace_events_filter.c

@@ -933,8 +933,9 @@ static void postfix_clear(struct filter_parse_state *ps)
 
 	while (!list_empty(&ps->postfix)) {
 		elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
-		kfree(elt->operand);
 		list_del(&elt->list);
+		kfree(elt->operand);
+		kfree(elt);
 	}
 }
 

kernel/trace/trace_hw_branches.c

@@ -165,6 +165,7 @@ void trace_hw_branch(u64 from, u64 to)
 	struct ftrace_event_call *call = &event_hw_branch;
 	struct trace_array *tr = hw_branch_trace;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buf;
 	struct hw_branch_entry *entry;
 	unsigned long irq1;
 	int cpu;
@@ -180,7 +181,8 @@ void trace_hw_branch(u64 from, u64 to)
 	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
 		goto out;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES,
+	buf = tr->buffer;
+	event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
@@ -189,8 +191,8 @@ void trace_hw_branch(u64 from, u64 to)
 	entry->ent.type = TRACE_HW_BRANCHES;
 	entry->from = from;
 	entry->to   = to;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buf, event))
+		trace_buffer_unlock_commit(buf, event, 0, 0);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);

kernel/trace/trace_output.c

@@ -486,16 +486,18 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 				hardirq ? 'h' : softirq ? 's' : '.'))
 		return 0;
 
-	if (entry->lock_depth < 0)
-		ret = trace_seq_putc(s, '.');
+	if (entry->preempt_count)
+		ret = trace_seq_printf(s, "%x", entry->preempt_count);
 	else
-		ret = trace_seq_printf(s, "%d", entry->lock_depth);
+		ret = trace_seq_putc(s, '.');
+
 	if (!ret)
 		return 0;
 
-	if (entry->preempt_count)
-		return trace_seq_printf(s, "%x", entry->preempt_count);
-	return trace_seq_putc(s, '.');
+	if (entry->lock_depth < 0)
+		return trace_seq_putc(s, '.');
+
+	return trace_seq_printf(s, "%d", entry->lock_depth);
 }
 
 static int
@@ -883,7 +885,7 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		task_state_char(field->prev_state);
+		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
 	if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
 			      field->prev_pid,
@@ -918,7 +920,7 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		task_state_char(field->prev_state);
+		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
 
 	SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);

kernel/trace/trace_stack.c

@@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = {
 
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
-		   struct file *file, void __user *buffer, size_t *lenp,
+		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos)
 {
 	int ret;
 
 	mutex_lock(&stack_sysctl_mutex);
 
-	ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write ||
 	    (last_stack_tracer_enabled == !!stack_tracer_enabled))

kernel/trace/trace_syscalls.c

@@ -166,7 +166,7 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
 			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
 			       SYSCALL_FIELD(int, nr),
-			       SYSCALL_FIELD(unsigned long, ret));
+			       SYSCALL_FIELD(long, ret));
 	if (!ret)
 		return 0;
 
@@ -212,7 +212,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
 	if (ret)
 		return ret;
 
-	ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0,
+	ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
 				 FILTER_OTHER);
 
 	return ret;