From 991821c86c2fb6cc4104ce679247864dbc070a83 Mon Sep 17 00:00:00 2001
From: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Date: Mon, 15 Jul 2013 16:32:34 +0800
Subject: tracing: Use correct config guard CONFIG_STACK_TRACER

We should use CONFIG_STACK_TRACER to guard readme text
of stack tracer related file, not CONFIG_STACKTRACE.

Link: http://lkml.kernel.org/r/51E3B3A2.8080609@huawei.com

Signed-off-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0cd500bffd9..25b91afc29e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3537,14 +3537,14 @@ static const char readme_msg[] =
 	"\n  snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
 	"\t\t\t  Read the contents for more information\n"
 #endif
-#ifdef CONFIG_STACKTRACE
+#ifdef CONFIG_STACK_TRACER
 	"  stack_trace\t\t- Shows the max stack trace when active\n"
 	"  stack_max_size\t- Shows current max stack size that was traced\n"
 	"\t\t\t  Write into this file to reset the max size (trigger a new trace)\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
 	"  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
 #endif
-#endif /* CONFIG_STACKTRACE */
+#endif /* CONFIG_STACK_TRACER */
 ;
 
 static ssize_t
-- 
cgit v1.2.3-70-g09d2


From 146c3442f2dd0f50d9431aea5d0d10dfd97c9999 Mon Sep 17 00:00:00 2001
From: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Date: Mon, 15 Jul 2013 16:32:44 +0800
Subject: tracing: Use trace_seq_puts()/trace_seq_putc() where possible

For string without format specifiers, use trace_seq_puts()
or trace_seq_putc().

Link: http://lkml.kernel.org/r/51E3B3AC.1000605@huawei.com

Signed-off-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
[ fixed a trace_seq_putc(s, " ") to trace_seq_putc(s, ' ') ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c           | 10 +++----
 kernel/trace/trace_events_filter.c   |  4 +--
 kernel/trace/trace_functions_graph.c | 52 ++++++++++++++++++------------------
 kernel/trace/trace_mmiotrace.c       |  8 +++---
 kernel/trace/trace_output.c          | 14 +++++-----
 kernel/trace/trace_syscalls.c        |  2 +-
 6 files changed, 45 insertions(+), 45 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e444ff88f0a..eef2e566b2e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -36,11 +36,11 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
 {
 	int ret;
 
-	ret = trace_seq_printf(s, "# compressed entry header\n");
-	ret = trace_seq_printf(s, "\ttype_len    :    5 bits\n");
-	ret = trace_seq_printf(s, "\ttime_delta  :   27 bits\n");
-	ret = trace_seq_printf(s, "\tarray       :   32 bits\n");
-	ret = trace_seq_printf(s, "\n");
+	ret = trace_seq_puts(s, "# compressed entry header\n");
+	ret = trace_seq_puts(s, "\ttype_len    :    5 bits\n");
+	ret = trace_seq_puts(s, "\ttime_delta  :   27 bits\n");
+	ret = trace_seq_puts(s, "\tarray       :   32 bits\n");
+	ret = trace_seq_putc(s, '\n');
 	ret = trace_seq_printf(s, "\tpadding     : type == %d\n",
 			       RINGBUF_TYPE_PADDING);
 	ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0d883dc057d..0c7b75a8acc 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -646,7 +646,7 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
-		trace_seq_printf(s, "none\n");
+		trace_seq_puts(s, "none\n");
 	mutex_unlock(&event_mutex);
 }
 
@@ -660,7 +660,7 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
-		trace_seq_printf(s, DEFAULT_SYS_FILTER_MESSAGE "\n");
+		trace_seq_puts(s, DEFAULT_SYS_FILTER_MESSAGE "\n");
 	mutex_unlock(&event_mutex);
 }
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 8388bc99f2e..d56ae9bae00 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -446,7 +446,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid)
 
 	/* First spaces to align center */
 	for (i = 0; i < spaces / 2; i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -457,7 +457,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid)
 
 	/* Last spaces to align center */
 	for (i = 0; i < spaces - (spaces / 2); i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -503,7 +503,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
  ------------------------------------------
 
  */
-	ret = trace_seq_printf(s,
+	ret = trace_seq_puts(s,
 		" ------------------------------------------\n");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -516,7 +516,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
 	if (ret == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	ret = trace_seq_printf(s, " => ");
+	ret = trace_seq_puts(s, " => ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -524,7 +524,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
 	if (ret == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	ret = trace_seq_printf(s,
+	ret = trace_seq_puts(s,
 		"\n ------------------------------------------\n\n");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -645,7 +645,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 			ret = print_graph_proc(s, pid);
 			if (ret == TRACE_TYPE_PARTIAL_LINE)
 				return TRACE_TYPE_PARTIAL_LINE;
-			ret = trace_seq_printf(s, " | ");
+			ret = trace_seq_puts(s, " | ");
 			if (!ret)
 				return TRACE_TYPE_PARTIAL_LINE;
 		}
@@ -657,9 +657,9 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		return ret;
 
 	if (type == TRACE_GRAPH_ENT)
-		ret = trace_seq_printf(s, "==========>");
+		ret = trace_seq_puts(s, "==========>");
 	else
-		ret = trace_seq_printf(s, "<==========");
+		ret = trace_seq_puts(s, "<==========");
 
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -668,7 +668,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	if (ret != TRACE_TYPE_HANDLED)
 		return ret;
 
-	ret = trace_seq_printf(s, "\n");
+	ret = trace_seq_putc(s, '\n');
 
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -705,13 +705,13 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 		len += strlen(nsecs_str);
 	}
 
-	ret = trace_seq_printf(s, " us ");
+	ret = trace_seq_puts(s, " us ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Print remaining spaces to fit the row's width */
 	for (i = len; i < 7; i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -731,13 +731,13 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
 	/* No real adata, just filling the column with spaces */
 	switch (duration) {
 	case DURATION_FILL_FULL:
-		ret = trace_seq_printf(s, "              |  ");
+		ret = trace_seq_puts(s, "              |  ");
 		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
 	case DURATION_FILL_START:
-		ret = trace_seq_printf(s, "  ");
+		ret = trace_seq_puts(s, "  ");
 		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
 	case DURATION_FILL_END:
-		ret = trace_seq_printf(s, " |");
+		ret = trace_seq_puts(s, " |");
 		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
 	}
 
@@ -745,10 +745,10 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
 	if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
 		/* Duration exceeded 100 msecs */
 		if (duration > 100000ULL)
-			ret = trace_seq_printf(s, "! ");
+			ret = trace_seq_puts(s, "! ");
 		/* Duration exceeded 10 msecs */
 		else if (duration > 10000ULL)
-			ret = trace_seq_printf(s, "+ ");
+			ret = trace_seq_puts(s, "+ ");
 	}
 
 	/*
@@ -757,7 +757,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
 	 * to fill out the space.
 	 */
 	if (ret == -1)
-		ret = trace_seq_printf(s, "  ");
+		ret = trace_seq_puts(s, "  ");
 
 	/* Catching here any failure happenned above */
 	if (!ret)
@@ -767,7 +767,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
 	if (ret != TRACE_TYPE_HANDLED)
 		return ret;
 
-	ret = trace_seq_printf(s, "|  ");
+	ret = trace_seq_puts(s, "|  ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -817,7 +817,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -858,7 +858,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -917,7 +917,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 		if (ret == TRACE_TYPE_PARTIAL_LINE)
 			return TRACE_TYPE_PARTIAL_LINE;
 
-		ret = trace_seq_printf(s, " | ");
+		ret = trace_seq_puts(s, " | ");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -1117,7 +1117,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 
 	/* Closing brace */
 	for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
-		ret = trace_seq_printf(s, " ");
+		ret = trace_seq_putc(s, ' ');
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -1129,7 +1129,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	 * belongs to, write out the function name.
 	 */
 	if (func_match) {
-		ret = trace_seq_printf(s, "}\n");
+		ret = trace_seq_puts(s, "}\n");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	} else {
@@ -1179,13 +1179,13 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 	/* Indentation */
 	if (depth > 0)
 		for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) {
-			ret = trace_seq_printf(s, " ");
+			ret = trace_seq_putc(s, ' ');
 			if (!ret)
 				return TRACE_TYPE_PARTIAL_LINE;
 		}
 
 	/* The comment */
-	ret = trace_seq_printf(s, "/* ");
+	ret = trace_seq_puts(s, "/* ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -1216,7 +1216,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 		s->len--;
 	}
 
-	ret = trace_seq_printf(s, " */\n");
+	ret = trace_seq_puts(s, " */\n");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index a5e8f4878bf..b3dcfb2f0fe 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -90,7 +90,7 @@ static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
 	if (drv)
 		ret += trace_seq_printf(s, " %s\n", drv->name);
 	else
-		ret += trace_seq_printf(s, " \n");
+		ret += trace_seq_puts(s, " \n");
 	return ret;
 }
 
@@ -107,7 +107,7 @@ static void mmio_pipe_open(struct trace_iterator *iter)
 	struct header_iter *hiter;
 	struct trace_seq *s = &iter->seq;
 
-	trace_seq_printf(s, "VERSION 20070824\n");
+	trace_seq_puts(s, "VERSION 20070824\n");
 
 	hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
 	if (!hiter)
@@ -209,7 +209,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
 			(rw->value >> 0) & 0xff, rw->pc, 0);
 		break;
 	default:
-		ret = trace_seq_printf(s, "rw what?\n");
+		ret = trace_seq_puts(s, "rw what?\n");
 		break;
 	}
 	if (ret)
@@ -245,7 +245,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter)
 			secs, usec_rem, m->map_id, 0UL, 0);
 		break;
 	default:
-		ret = trace_seq_printf(s, "map what?\n");
+		ret = trace_seq_puts(s, "map what?\n");
 		break;
 	}
 	if (ret)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index bb922d9ee51..34e7cbac0c9 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -78,7 +78,7 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
 
 	trace_assign_type(field, entry);
 
-	ret = trace_seq_printf(s, "%s", field->buf);
+	ret = trace_seq_puts(s, field->buf);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -558,14 +558,14 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 			if (ret)
 				ret = trace_seq_puts(s, "??");
 			if (ret)
-				ret = trace_seq_puts(s, "\n");
+				ret = trace_seq_putc(s, '\n');
 			continue;
 		}
 		if (!ret)
 			break;
 		if (ret)
 			ret = seq_print_user_ip(s, mm, ip, sym_flags);
-		ret = trace_seq_puts(s, "\n");
+		ret = trace_seq_putc(s, '\n');
 	}
 
 	if (mm)
@@ -579,7 +579,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	int ret;
 
 	if (!ip)
-		return trace_seq_printf(s, "0");
+		return trace_seq_putc(s, '0');
 
 	if (sym_flags & TRACE_ITER_SYM_OFFSET)
 		ret = seq_print_sym_offset(s, "%s", ip);
@@ -964,14 +964,14 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
 		goto partial;
 
 	if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) {
-		if (!trace_seq_printf(s, " <-"))
+		if (!trace_seq_puts(s, " <-"))
 			goto partial;
 		if (!seq_print_ip_sym(s,
 				      field->parent_ip,
 				      flags))
 			goto partial;
 	}
-	if (!trace_seq_printf(s, "\n"))
+	if (!trace_seq_putc(s, '\n'))
 		goto partial;
 
 	return TRACE_TYPE_HANDLED;
@@ -1210,7 +1210,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 		if (!seq_print_ip_sym(s, *p, flags))
 			goto partial;
-		if (!trace_seq_puts(s, "\n"))
+		if (!trace_seq_putc(s, '\n'))
 			goto partial;
 	}
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 322e1646107..06115621572 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -175,7 +175,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 	entry = syscall_nr_to_meta(syscall);
 
 	if (!entry) {
-		trace_seq_printf(s, "\n");
+		trace_seq_putc(s, '\n');
 		return TRACE_TYPE_HANDLED;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From d611851b421731e2afd9cb956daae001af57a423 Mon Sep 17 00:00:00 2001
From: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Date: Mon, 15 Jul 2013 16:32:50 +0800
Subject: tracing: Typo fix on ring buffer comments

There have some mismatch between comments with
real function name, update it.

This patch also add some missed function arguments
description.

Link: http://lkml.kernel.org/r/51E3B3B2.4080307@huawei.com

Signed-off-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index eef2e566b2e..cc2f66f68dc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1066,7 +1066,7 @@ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
 }
 
 /**
- * check_pages - integrity check of buffer pages
+ * rb_check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
  *
  * As a safety measure we check to make sure the data pages have not
@@ -1258,7 +1258,7 @@ static int rb_cpu_notify(struct notifier_block *self,
 #endif
 
 /**
- * ring_buffer_alloc - allocate a new ring_buffer
+ * __ring_buffer_alloc - allocate a new ring_buffer
  * @size: the size in bytes per cpu that is needed.
  * @flags: attributes to set for the ring buffer.
  *
@@ -1607,6 +1607,7 @@ static void update_pages_handler(struct work_struct *work)
  * ring_buffer_resize - resize the ring buffer
  * @buffer: the buffer to resize.
  * @size: the new size.
+ * @cpu_id: the cpu buffer to resize
  *
  * Minimum size is 2 * BUF_PAGE_SIZE.
  *
@@ -3956,11 +3957,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
  * expected.
  *
  * After a sequence of ring_buffer_read_prepare calls, the user is
- * expected to make at least one call to ring_buffer_prepare_sync.
+ * expected to make at least one call to ring_buffer_read_prepare_sync.
  * Afterwards, ring_buffer_read_start is invoked to get things going
  * for real.
  *
- * This overall must be paired with ring_buffer_finish.
+ * This overall must be paired with ring_buffer_read_finish.
  */
 struct ring_buffer_iter *
 ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
@@ -4009,7 +4010,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
  * an intervening ring_buffer_read_prepare_sync must have been
  * performed.
  *
- * Must be paired with ring_buffer_finish.
+ * Must be paired with ring_buffer_read_finish.
  */
 void
 ring_buffer_read_start(struct ring_buffer_iter *iter)
@@ -4031,7 +4032,7 @@ ring_buffer_read_start(struct ring_buffer_iter *iter)
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
 /**
- * ring_buffer_finish - finish reading the iterator of the buffer
+ * ring_buffer_read_finish - finish reading the iterator of the buffer
  * @iter: The iterator retrieved by ring_buffer_start
  *
  * This re-enables the recording to the buffer, and frees the
@@ -4346,6 +4347,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
  * @buffer: the buffer to allocate for.
+ * @cpu: the cpu buffer to allocate.
  *
  * This function is used in conjunction with ring_buffer_read_page.
  * When reading a full page from the ring buffer, these functions
@@ -4403,7 +4405,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  * to swap with a page in the ring buffer.
  *
  * for example:
- *	rpage = ring_buffer_alloc_read_page(buffer);
+ *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
  *	if (!rpage)
  *		return error;
  *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
-- 
cgit v1.2.3-70-g09d2


From b8ebfd3f7113b63dda93d76bfec638c00e6bd514 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 17 Jun 2013 19:02:04 +0200
Subject: tracing/function: Avoid perf_trace_buf_*() if
 event_function.perf_events is empty

perf_trace_buf_prepare() + perf_trace_buf_submit(head, task => NULL)
make no sense if hlist_empty(head). Change perf_ftrace_function_call()
to check event_function.perf_events beforehand.

Link: http://lkml.kernel.org/r/20130617170204.GA19803@redhat.com

Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_event_perf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 84b1e045fab..12df5573086 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -266,6 +266,10 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 	struct pt_regs regs;
 	int rctx;
 
+	head = this_cpu_ptr(event_function.perf_events);
+	if (hlist_empty(head))
+		return;
+
 #define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
 		    sizeof(u64)) - sizeof(u32))
 
@@ -279,8 +283,6 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 
 	entry->ip = ip;
 	entry->parent_ip = parent_ip;
-
-	head = this_cpu_ptr(event_function.perf_events);
 	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
 			      1, &regs, head, NULL);
 
-- 
cgit v1.2.3-70-g09d2


From 421c7860c6e1989da3962fafdd6699316c9f8e20 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 17 Jun 2013 19:02:07 +0200
Subject: tracing/syscall: Avoid perf_trace_buf_*() if sys_data->perf_events is
 empty

perf_trace_buf_prepare() + perf_trace_buf_submit(head, task => NULL)
make no sense if hlist_empty(head). Change perf_syscall_enter/exit()
to check sys_data->{enter,exit}_event->perf_events beforehand.

Link: http://lkml.kernel.org/r/20130617170207.GA19806@redhat.com

Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_syscalls.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 06115621572..ac0085777fb 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -566,6 +566,10 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
+	head = this_cpu_ptr(sys_data->enter_event->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	/* get the size after alignment with the u32 buffer size field */
 	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
@@ -583,8 +587,6 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
-
-	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
@@ -642,6 +644,10 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	head = this_cpu_ptr(sys_data->exit_event->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	/* We can probably do that at build time */
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
@@ -661,8 +667,6 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
-
-	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
-- 
cgit v1.2.3-70-g09d2


From cd92bf61d6d70bd3eb33b46d600e3f3eb9c5778a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 17 Jun 2013 19:02:11 +0200
Subject: tracing/perf: Move the PERF_MAX_TRACE_SIZE check into
 perf_trace_buf_prepare()

Every perf_trace_buf_prepare() caller does
WARN_ONCE(size > PERF_MAX_TRACE_SIZE, message) and "message" is
almost the same.

Shift this WARN_ONCE() into perf_trace_buf_prepare(). This changes
the meaning of _ONCE, but I think this is fine.

	- 4947014 2932448 10104832  17984294  1126b26 vmlinux
	+ 4948422 2932448 10104832  17985702  11270a6 vmlinux

on my build.

Link: http://lkml.kernel.org/r/20130617170211.GA19813@redhat.com

Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/ftrace.h          |  4 ----
 kernel/trace/trace_event_perf.c |  4 ++++
 kernel/trace/trace_kprobe.c     |  6 ------
 kernel/trace/trace_syscalls.c   | 12 ------------
 kernel/trace/trace_uprobe.c     |  2 --
 5 files changed, 4 insertions(+), 24 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index d615f78cc6b..41a6643e213 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -670,10 +670,6 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,		\
-		      "profile buffer not large enough"))		\
-		return;							\
-									\
 	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
 		__entry_size, event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 12df5573086..80c36bcf66e 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -236,6 +236,10 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 
 	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+			"perf buffer not large enough"))
+		return NULL;
+
 	pc = preempt_count();
 
 	*rctxp = perf_swevent_get_recursion_context();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7ed6976493c..ae6ce835b02 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1087,9 +1087,6 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
 	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		     "profile buffer not large enough"))
-		return;
 
 	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
 	if (!entry)
@@ -1120,9 +1117,6 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		     "profile buffer not large enough"))
-		return;
 
 	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
 	if (!entry)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ac0085777fb..8fd03657bc7 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -575,10 +575,6 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		      "perf buffer not large enough"))
-		return;
-
 	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
 				sys_data->enter_event->event.type, regs, &rctx);
 	if (!rec)
@@ -652,14 +648,6 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	/*
-	 * Impossible, but be paranoid with the future
-	 * How to put this check outside runtime?
-	 */
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		"exit event has grown above perf buffer size"))
-		return;
-
 	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
 				sys_data->exit_event->event.type, regs, &rctx);
 	if (!rec)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d5d0cd368a5..a23d2d71188 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -818,8 +818,6 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
 
 	size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 	size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
-		return;
 
 	preempt_disable();
 	head = this_cpu_ptr(call->perf_events);
-- 
cgit v1.2.3-70-g09d2


From a232e270dcb55a70ad3241bc6fc160fd9b5c9e6c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Tue, 9 Jul 2013 18:35:26 +0900
Subject: tracing/kprobe: Wait for disabling all running kprobe handlers

Wait for disabling all running kprobe handlers when a kprobe
event is disabled, since the caller, trace_remove_event_call()
supposes that a removing event is disabled completely by
disabling the event.
With this change, ftrace can ensure that there is no running
event handlers after disabling it.

Link: http://lkml.kernel.org/r/20130709093526.20138.93100.stgit@mhiramat-M0-7522

Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ae6ce835b02..3811487e7a7 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -243,11 +243,11 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
 static int
 disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 {
+	struct event_file_link *link = NULL;
+	int wait = 0;
 	int ret = 0;
 
 	if (file) {
-		struct event_file_link *link;
-
 		link = find_event_file_link(tp, file);
 		if (!link) {
 			ret = -EINVAL;
@@ -255,10 +255,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 		}
 
 		list_del_rcu(&link->list);
-		/* synchronize with kprobe_trace_func/kretprobe_trace_func */
-		synchronize_sched();
-		kfree(link);
-
+		wait = 1;
 		if (!list_empty(&tp->files))
 			goto out;
 
@@ -271,8 +268,22 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 			disable_kretprobe(&tp->rp);
 		else
 			disable_kprobe(&tp->rp.kp);
+		wait = 1;
 	}
  out:
+	if (wait) {
+		/*
+		 * Synchronize with kprobe_trace_func/kretprobe_trace_func
+		 * to ensure disabled (all running handlers are finished).
+		 * This is not only for kfree(), but also the caller,
+		 * trace_remove_event_call() supposes it for releasing
+		 * event_call related objects, which will be accessed in
+		 * the kprobe_trace_func/kretprobe_trace_func.
+		 */
+		synchronize_sched();
+		kfree(link);	/* Ignored if link == NULL */
+	}
+
 	return ret;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 609e85a70bcd0eedf4ec60639dbcfb1ab011e054 Mon Sep 17 00:00:00 2001
From: Alexander Z Lam <azl@google.com>
Date: Wed, 10 Jul 2013 17:34:34 -0700
Subject: tracing: Fix error handling to ensure instances can always be removed

Remove debugfs directories for tracing instances during creation if an error
occurs causing the trace_array for that instance to not be added to
ftrace_trace_arrays. If the directory continues to exist after the error, it
cannot be removed because the respective trace_array is not in
ftrace_trace_arrays.

Link: http://lkml.kernel.org/r/1373502874-1706-2-git-send-email-azl@google.com

Cc: stable@vger.kernel.org # 3.10
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Cc: David Sharp <dhsharp@google.com>
Cc: Alexander Z Lam <lambchop468@gmail.com>
Signed-off-by: Alexander Z Lam <azl@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 25b91afc29e..7c3da7bca05 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5973,8 +5973,10 @@ static int new_instance_create(const char *name)
 		goto out_free_tr;
 
 	ret = event_trace_add_tracer(tr->dir, tr);
-	if (ret)
+	if (ret) {
+		debugfs_remove_recursive(tr->dir);
 		goto out_free_tr;
+	}
 
 	init_tracer_debugfs(tr, tr->dir);
 
-- 
cgit v1.2.3-70-g09d2


From f77d09a384676bde6445413949d9d2c508ff3e62 Mon Sep 17 00:00:00 2001
From: Alexander Z Lam <azl@google.com>
Date: Thu, 18 Jul 2013 11:18:44 -0700
Subject: tracing: Miscellaneous fixes for trace_array ref counting

Some error paths did not handle ref counting properly, and some trace files need
ref counting.

Link: http://lkml.kernel.org/r/1374171524-11948-1-git-send-email-azl@google.com

Cc: stable@vger.kernel.org # 3.10
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Cc: David Sharp <dhsharp@google.com>
Cc: Alexander Z Lam <lambchop468@gmail.com>
Signed-off-by: Alexander Z Lam <azl@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c        | 24 ++++++++++++++++++------
 kernel/trace/trace_events.c | 21 +++++++++++++++++++--
 2 files changed, 37 insertions(+), 8 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7c3da7bca05..7d9ceab4256 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3008,7 +3008,6 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	iter = m->private;
 	tr = iter->tr;
-	trace_array_put(tr);
 
 	mutex_lock(&trace_types_lock);
 
@@ -3023,6 +3022,9 @@ static int tracing_release(struct inode *inode, struct file *file)
 	if (!iter->snapshot)
 		/* reenable tracing if it was previously enabled */
 		tracing_start_tr(tr);
+
+	__trace_array_put(tr);
+
 	mutex_unlock(&trace_types_lock);
 
 	mutex_destroy(&iter->mutex);
@@ -3447,6 +3449,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 static int tracing_trace_options_open(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
+	int ret;
 
 	if (tracing_disabled)
 		return -ENODEV;
@@ -3454,7 +3457,11 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
 	if (trace_array_get(tr) < 0)
 		return -ENODEV;
 
-	return single_open(file, tracing_trace_options_show, inode->i_private);
+	ret = single_open(file, tracing_trace_options_show, inode->i_private);
+	if (ret < 0)
+		trace_array_put(tr);
+
+	return ret;
 }
 
 static const struct file_operations tracing_iter_fops = {
@@ -3958,6 +3965,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter) {
 		ret = -ENOMEM;
+		__trace_array_put(tr);
 		goto out;
 	}
 
@@ -4704,21 +4712,24 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 			ret = PTR_ERR(iter);
 	} else {
 		/* Writes still need the seq_file to hold the private data */
+		ret = -ENOMEM;
 		m = kzalloc(sizeof(*m), GFP_KERNEL);
 		if (!m)
-			return -ENOMEM;
+			goto out;
 		iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 		if (!iter) {
 			kfree(m);
-			return -ENOMEM;
+			goto out;
 		}
+		ret = 0;
+
 		iter->tr = tr;
 		iter->trace_buffer = &tc->tr->max_buffer;
 		iter->cpu_file = tc->cpu;
 		m->private = iter;
 		file->private_data = m;
 	}
-
+out:
 	if (ret < 0)
 		trace_array_put(tr);
 
@@ -5328,9 +5339,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 }
 
 static const struct file_operations tracing_stats_fops = {
-	.open		= tracing_open_generic,
+	.open		= tracing_open_generic_tc,
 	.read		= tracing_stats_read,
 	.llseek		= generic_file_llseek,
+	.release	= tracing_release_generic_tc,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7d854290bf8..7a75cb22eab 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1218,6 +1218,7 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 static int ftrace_event_avail_open(struct inode *inode, struct file *file);
 static int ftrace_event_set_open(struct inode *inode, struct file *file);
+static int ftrace_event_release(struct inode *inode, struct file *file);
 
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
@@ -1245,7 +1246,7 @@ static const struct file_operations ftrace_set_event_fops = {
 	.read = seq_read,
 	.write = ftrace_event_write,
 	.llseek = seq_lseek,
-	.release = seq_release,
+	.release = ftrace_event_release,
 };
 
 static const struct file_operations ftrace_enable_fops = {
@@ -1323,6 +1324,15 @@ ftrace_event_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
+static int ftrace_event_release(struct inode *inode, struct file *file)
+{
+	struct trace_array *tr = inode->i_private;
+
+	trace_array_put(tr);
+
+	return seq_release(inode, file);
+}
+
 static int
 ftrace_event_avail_open(struct inode *inode, struct file *file)
 {
@@ -1336,12 +1346,19 @@ ftrace_event_set_open(struct inode *inode, struct file *file)
 {
 	const struct seq_operations *seq_ops = &show_set_event_seq_ops;
 	struct trace_array *tr = inode->i_private;
+	int ret;
+
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
 		ftrace_clear_events(tr);
 
-	return ftrace_event_open(inode, file, seq_ops);
+	ret = ftrace_event_open(inode, file, seq_ops);
+	if (ret < 0)
+		trace_array_put(tr);
+	return ret;
 }
 
 static struct event_subsystem *
-- 
cgit v1.2.3-70-g09d2


From 8f768993394a8c0d3801033c11fd86ce8c88dcac Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Thu, 18 Jul 2013 14:41:51 -0400
Subject: tracing: Add ref_data to function and fgraph tracer structs

The selftest for function and function graph tracers are defined as
__init, as they are only executed at boot up. The "tracer" structs
that are associated to those tracers are not setup as __init as they
are used after boot. To stop mismatch warnings, those structures
need to be annotated with __ref_data.

Currently, the tracer structures are defined to __read_mostly, as they
do not really change. But in the future they should be converted to
consts, but that will take a little work because they have a "next"
pointer that gets updated when they are registered. That will have to
wait till the next major release.

Link: http://lkml.kernel.org/r/1373596735.17876.84.camel@gandalf.local.home

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Reported-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.h                 | 9 +++++++++
 kernel/trace/trace_functions.c       | 2 +-
 kernel/trace/trace_functions_graph.c | 2 +-
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4a4f6e1828b..57b7bb0d39b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -680,6 +680,15 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
+/*
+ * Tracer data references selftest functions that only occur
+ * on boot up. These can be __init functions. Thus, when selftests
+ * are enabled, then the tracers need to reference __init functions.
+ */
+#define __tracer_data		__refdata
+#else
+/* Tracers are seldom changed. Optimize when selftests are disabled. */
+#define __tracer_data		__read_mostly
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index b863f93b30f..38fe1483c50 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -199,7 +199,7 @@ static int func_set_flag(u32 old_flags, u32 bit, int set)
 	return 0;
 }
 
-static struct tracer function_trace __read_mostly =
+static struct tracer function_trace __tracer_data =
 {
 	.name		= "function",
 	.init		= function_trace_init,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d56ae9bae00..b5c09242683 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1448,7 +1448,7 @@ static struct trace_event graph_trace_ret_event = {
 	.funcs		= &graph_functions
 };
 
-static struct tracer graph_trace __read_mostly = {
+static struct tracer graph_trace __tracer_data = {
 	.name		= "function_graph",
 	.open		= graph_trace_open,
 	.pipe_open	= graph_trace_open,
-- 
cgit v1.2.3-70-g09d2


From 7710b639953b791610f0022a7d52d9801c93b969 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 18 Jul 2013 20:47:10 +0200
Subject: tracing: Simplify the iteration logic in f_start/f_next

f_next() looks overcomplicated, and it is not strictly correct
even if this doesn't matter.

Say, FORMAT_FIELD_SEPERATOR should not return NULL (means EOF)
if trace_get_fields() returns an empty list, we should simply
advance to FORMAT_PRINTFMT as we do when we find the end of list.

1. Change f_next() to return "struct list_head *" rather than
   "ftrace_event_field *", and change f_show() to do list_entry().

   This simplifies the code a bit, only f_show() needs to know
   about ftrace_event_field, and f_next() can play with ->prev
   directly

2. Change f_next() to not play with ->prev / return inside the
   switch() statement. It can simply set node = head/common_head,
   the prev-or-advance-to-the-next-magic below does all work.

While at it. f_start() looks overcomplicated too. I don't think
*pos == 0 makes sense as a separate case, just change this code
to do "while" instead of "do/while".

The patch also moves f_start() down, close to f_stop(). This is
purely cosmetic, just to make the locking added by the next patch
more clear/visible.

Link: http://lkml.kernel.org/r/20130718184710.GA4783@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 60 +++++++++++++++++----------------------------
 1 file changed, 22 insertions(+), 38 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7a75cb22eab..76defd91f9b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -826,59 +826,33 @@ enum {
 static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct ftrace_event_call *call = m->private;
-	struct ftrace_event_field *field;
 	struct list_head *common_head = &ftrace_common_fields;
 	struct list_head *head = trace_get_fields(call);
+	struct list_head *node = v;
 
 	(*pos)++;
 
 	switch ((unsigned long)v) {
 	case FORMAT_HEADER:
-		if (unlikely(list_empty(common_head)))
-			return NULL;
-
-		field = list_entry(common_head->prev,
-				   struct ftrace_event_field, link);
-		return field;
+		node = common_head;
+		break;
 
 	case FORMAT_FIELD_SEPERATOR:
-		if (unlikely(list_empty(head)))
-			return NULL;
-
-		field = list_entry(head->prev, struct ftrace_event_field, link);
-		return field;
+		node = head;
+		break;
 
 	case FORMAT_PRINTFMT:
 		/* all done */
 		return NULL;
 	}
 
-	field = v;
-	if (field->link.prev == common_head)
+	node = node->prev;
+	if (node == common_head)
 		return (void *)FORMAT_FIELD_SEPERATOR;
-	else if (field->link.prev == head)
+	else if (node == head)
 		return (void *)FORMAT_PRINTFMT;
-
-	field = list_entry(field->link.prev, struct ftrace_event_field, link);
-
-	return field;
-}
-
-static void *f_start(struct seq_file *m, loff_t *pos)
-{
-	loff_t l = 0;
-	void *p;
-
-	/* Start by showing the header */
-	if (!*pos)
-		return (void *)FORMAT_HEADER;
-
-	p = (void *)FORMAT_HEADER;
-	do {
-		p = f_next(m, p, &l);
-	} while (p && l < *pos);
-
-	return p;
+	else
+		return node;
 }
 
 static int f_show(struct seq_file *m, void *v)
@@ -904,8 +878,7 @@ static int f_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
-	field = v;
-
+	field = list_entry(v, struct ftrace_event_field, link);
 	/*
 	 * Smartly shows the array type(except dynamic array).
 	 * Normal:
@@ -932,6 +905,17 @@ static int f_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+static void *f_start(struct seq_file *m, loff_t *pos)
+{
+	void *p = (void *)FORMAT_HEADER;
+	loff_t l = 0;
+
+	while (l < *pos && p)
+		p = f_next(m, p, &l);
+
+	return p;
+}
+
 static void f_stop(struct seq_file *m, void *p)
 {
 }
-- 
cgit v1.2.3-70-g09d2


From cd458ba9d5a5592d37b5145e560071e91ea762ac Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 18 Jul 2013 20:47:12 +0200
Subject: tracing: Do not (ab)use trace_seq in event_id_read()

event_id_read() has no reason to kmalloc "struct trace_seq"
(more than PAGE_SIZE!), it can use a small buffer instead.

Note: "if (*ppos) return 0" looks strange and even wrong,
simple_read_from_buffer() handles ppos != 0 case corrrectly.

And it seems that almost every user of trace_seq in this file
should be converted too. Unless you use seq_open(), trace_seq
buys nothing compared to the raw buffer, but it needs a bit
more memory and code.

Link: http://lkml.kernel.org/r/20130718184712.GA4786@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 76defd91f9b..898f868833f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -947,23 +947,14 @@ static ssize_t
 event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
-	struct trace_seq *s;
-	int r;
+	char buf[32];
+	int len;
 
 	if (*ppos)
 		return 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	trace_seq_init(s);
-	trace_seq_printf(s, "%d\n", call->event.type);
-
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    s->buffer, s->len);
-	kfree(s);
-	return r;
+	len = sprintf(buf, "%d\n", call->event.type);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
 }
 
 static ssize_t
-- 
cgit v1.2.3-70-g09d2


From a644a7e9587802eabb2e229177606f6a74a60fc1 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 19 Jul 2013 16:20:36 +0200
Subject: tracing: Kill trace_array->waiter

Trivial. trace_array->waiter has no users since 6eaaa5d5
"tracing/core: use appropriate waiting on trace_pipe".

Link: http://lkml.kernel.org/r/20130719142036.GA1594@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57b7bb0d39b..e7d643b8a90 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -214,7 +214,6 @@ struct trace_array {
 	struct dentry		*event_dir;
 	struct list_head	systems;
 	struct list_head	events;
-	struct task_struct	*waiter;
 	int			ref;
 };
 
-- 
cgit v1.2.3-70-g09d2


From e70e78e3c83b536730e31231dd9b979768d8df3c Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 19 Jul 2013 17:36:44 +0200
Subject: tracing: Kill the unbalanced tr->ref++ in tracing_buffers_open()

tracing_buffers_open() does trace_array_get() and then it wrongly
inrcements tr->ref again under trace_types_lock. This means that
every caller leaks trace_array:

	# cd /sys/kernel/debug/tracing/
	# mkdir instances/X
	# true < instances/X/per_cpu/cpu0/trace_pipe_raw
	# rmdir instances/X
	rmdir: failed to remove `instances/X': Device or resource busy

Link: http://lkml.kernel.org/r/20130719153644.GA18899@redhat.com

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: stable@vger.kernel.org # 3.10
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7d9ceab4256..3f2477713ac 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4959,8 +4959,6 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	mutex_lock(&trace_types_lock);
 
-	tr->ref++;
-
 	info->iter.tr		= tr;
 	info->iter.cpu_file	= tc->cpu;
 	info->iter.trace	= tr->current_trace;
-- 
cgit v1.2.3-70-g09d2


From 649e9c70da6bfbeb563193a35d3424a5aa7c0d38 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:25:54 +0200
Subject: tracing: Introduce trace_create_cpu_file() and tracing_get_cpu()

Every "file_operations" used by tracing_init_debugfs_percpu is buggy.
f_op->open/etc does:

	1. struct trace_cpu *tc = inode->i_private;
	   struct trace_array *tr = tc->tr;

	2. trace_array_get(tr) or fail;

	3. do_something(tc);

But tc (and tr) can be already freed before trace_array_get() is called.
And it doesn't matter whether this file is per-cpu or it was created by
init_tracer_debugfs(), free_percpu() or kfree() are equally bad.

Note that even 1. is not safe, the freed memory can be unmapped. But even
if it was safe trace_array_get() can wrongly succeed if we also race with
the next new_instance_create() which can re-allocate the same tr, or tc
was overwritten and ->tr points to the valid tr. In this case 3. uses the
freed/reused memory.

Add the new trivial helper, trace_create_cpu_file() which simply calls
trace_create_file() and encodes "cpu" in "struct inode". Another helper,
tracing_get_cpu() will be used to read cpu_nr-or-RING_BUFFER_ALL_CPUS.

The patch abuses ->i_cdev to encode the number, it is never used unless
the file is S_ISCHR(). But we could use something else, say, i_bytes or
even ->d_fsdata. In any case this hack is hidden inside these 2 helpers,
it would be trivial to change them if needed.

This patch only changes tracing_init_debugfs_percpu() to use the new
trace_create_cpu_file(), the next patches will change file_operations.

Note: tracing_get_cpu(inode) is always safe but you can't trust the
result unless trace_array_get() was called, without trace_types_lock
which acts as a barrier it can wrongly return RING_BUFFER_ALL_CPUS.

Link: http://lkml.kernel.org/r/20130723152554.GA23710@redhat.com

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 50 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 14 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3f2477713ac..cfff63c2148 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2843,6 +2843,17 @@ static int s_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+/*
+ * Should be used after trace_array_get(), trace_types_lock
+ * ensures that i_cdev was already initialized.
+ */
+static inline int tracing_get_cpu(struct inode *inode)
+{
+	if (inode->i_cdev) /* See trace_create_cpu_file() */
+		return (long)inode->i_cdev - 1;
+	return RING_BUFFER_ALL_CPUS;
+}
+
 static const struct seq_operations tracer_seq_ops = {
 	.start		= s_start,
 	.next		= s_next,
@@ -5529,6 +5540,17 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
 	return tr->percpu_dir;
 }
 
+static struct dentry *
+trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
+		      void *data, long cpu, const struct file_operations *fops)
+{
+	struct dentry *ret = trace_create_file(name, mode, parent, data, fops);
+
+	if (ret) /* See tracing_get_cpu() */
+		ret->d_inode->i_cdev = (void *)(cpu + 1);
+	return ret;
+}
+
 static void
 tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 {
@@ -5548,28 +5570,28 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	trace_create_file("trace_pipe", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_pipe_fops);
+	trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+				&data->trace_cpu, cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	trace_create_file("trace", 0644, d_cpu,
-			(void *)&data->trace_cpu, &tracing_fops);
+	trace_create_cpu_file("trace", 0644, d_cpu,
+				&data->trace_cpu, cpu, &tracing_fops);
 
-	trace_create_file("trace_pipe_raw", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_buffers_fops);
+	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+				&data->trace_cpu, cpu, &tracing_buffers_fops);
 
-	trace_create_file("stats", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_stats_fops);
+	trace_create_cpu_file("stats", 0444, d_cpu,
+				&data->trace_cpu, cpu, &tracing_stats_fops);
 
-	trace_create_file("buffer_size_kb", 0444, d_cpu,
-			(void *)&data->trace_cpu, &tracing_entries_fops);
+	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+				&data->trace_cpu, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", 0644, d_cpu,
-			  (void *)&data->trace_cpu, &snapshot_fops);
+	trace_create_cpu_file("snapshot", 0644, d_cpu,
+				&data->trace_cpu, cpu, &snapshot_fops);
 
-	trace_create_file("snapshot_raw", 0444, d_cpu,
-			(void *)&data->trace_cpu, &snapshot_raw_fops);
+	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+				&data->trace_cpu, cpu, &snapshot_raw_fops);
 #endif
 }
 
-- 
cgit v1.2.3-70-g09d2


From 15544209cb0b5312e5220a9337a1fe61d1a1f2d9 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:25:57 +0200
Subject: tracing: Change tracing_pipe_fops() to rely on tracing_get_cpu()

tracing_open_pipe() is racy, the memory inode->i_private points to
can be already freed.

Change debugfs_create_file("trace_pipe", data) callers to to pass
"data = tr", tracing_open_pipe() can use tracing_get_cpu().

Link: http://lkml.kernel.org/r/20130723152557.GA23717@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index cfff63c2148..51a99ef2a6e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3959,8 +3959,7 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int ret = 0;
 
@@ -4006,9 +4005,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	iter->cpu_file = tc->cpu;
-	iter->tr = tc->tr;
-	iter->trace_buffer = &tc->tr->trace_buffer;
+	iter->tr = tr;
+	iter->trace_buffer = &tr->trace_buffer;
+	iter->cpu_file = tracing_get_cpu(inode);
 	mutex_init(&iter->mutex);
 	filp->private_data = iter;
 
@@ -4031,8 +4030,7 @@ fail:
 static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
 	struct trace_iterator *iter = file->private_data;
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 
 	mutex_lock(&trace_types_lock);
 
@@ -5571,7 +5569,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 
 	/* per cpu trace_pipe */
 	trace_create_cpu_file("trace_pipe", 0444, d_cpu,
-				&data->trace_cpu, cpu, &tracing_pipe_fops);
+				tr, cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
 	trace_create_cpu_file("trace", 0644, d_cpu,
@@ -6157,7 +6155,7 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			(void *)&tr->trace_cpu, &tracing_fops);
 
 	trace_create_file("trace_pipe", 0444, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_pipe_fops);
+			  tr, &tracing_pipe_fops);
 
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
 			(void *)&tr->trace_cpu, &tracing_entries_fops);
-- 
cgit v1.2.3-70-g09d2


From 46ef2be0d1d5ccea0c41bb606143586daadd537c Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:26:00 +0200
Subject: tracing: Change tracing_buffers_fops to rely on tracing_get_cpu()

tracing_buffers_open() is racy, the memory inode->i_private points
to can be already freed.

Change debugfs_create_file("trace_pipe_raw", data) caller to pass
"data = tr", tracing_buffers_open() can use tracing_get_cpu().

Change debugfs_create_file("snapshot_raw_fops", data) caller too,
this file uses tracing_buffers_open/release.

Link: http://lkml.kernel.org/r/20130723152600.GA23720@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 51a99ef2a6e..30c058a56ff 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4949,8 +4949,7 @@ static const struct file_operations snapshot_raw_fops = {
 
 static int tracing_buffers_open(struct inode *inode, struct file *filp)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct ftrace_buffer_info *info;
 	int ret;
 
@@ -4969,7 +4968,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	mutex_lock(&trace_types_lock);
 
 	info->iter.tr		= tr;
-	info->iter.cpu_file	= tc->cpu;
+	info->iter.cpu_file	= tracing_get_cpu(inode);
 	info->iter.trace	= tr->current_trace;
 	info->iter.trace_buffer = &tr->trace_buffer;
 	info->spare		= NULL;
@@ -5576,7 +5575,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 				&data->trace_cpu, cpu, &tracing_fops);
 
 	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
-				&data->trace_cpu, cpu, &tracing_buffers_fops);
+				tr, cpu, &tracing_buffers_fops);
 
 	trace_create_cpu_file("stats", 0444, d_cpu,
 				&data->trace_cpu, cpu, &tracing_stats_fops);
@@ -5589,7 +5588,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 				&data->trace_cpu, cpu, &snapshot_fops);
 
 	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
-				&data->trace_cpu, cpu, &snapshot_raw_fops);
+				tr, cpu, &snapshot_raw_fops);
 #endif
 }
 
-- 
cgit v1.2.3-70-g09d2


From 4d3435b8a4c3357695e09c5e7a3bf73a19fca5b0 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:26:03 +0200
Subject: tracing: Change tracing_stats_fops to rely on tracing_get_cpu()

tracing_open_generic_tc() is racy, the memory inode->i_private
points to can be already freed.

1. Change one of its users, tracing_stats_fops, to use
   tracing_*_generic_tr() instead.

2. Change trace_create_cpu_file("stats", data) to pass "data = tr".

3. Change tracing_stats_read() to use tracing_get_cpu().

Link: http://lkml.kernel.org/r/20130723152603.GA23727@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 30c058a56ff..e29dc8f69aa 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2982,7 +2982,6 @@ static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 	filp->private_data = inode->i_private;
 
 	return 0;
-	
 }
 
 static int tracing_open_generic_tc(struct inode *inode, struct file *filp)
@@ -5285,14 +5284,14 @@ static ssize_t
 tracing_stats_read(struct file *filp, char __user *ubuf,
 		   size_t count, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
-	struct trace_array *tr = tc->tr;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
 	struct trace_buffer *trace_buf = &tr->trace_buffer;
+	int cpu = tracing_get_cpu(inode);
 	struct trace_seq *s;
 	unsigned long cnt;
 	unsigned long long t;
 	unsigned long usec_rem;
-	int cpu = tc->cpu;
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
@@ -5345,10 +5344,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 }
 
 static const struct file_operations tracing_stats_fops = {
-	.open		= tracing_open_generic_tc,
+	.open		= tracing_open_generic_tr,
 	.read		= tracing_stats_read,
 	.llseek		= generic_file_llseek,
-	.release	= tracing_release_generic_tc,
+	.release	= tracing_release_generic_tr,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -5578,7 +5577,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 				tr, cpu, &tracing_buffers_fops);
 
 	trace_create_cpu_file("stats", 0444, d_cpu,
-				&data->trace_cpu, cpu, &tracing_stats_fops);
+				tr, cpu, &tracing_stats_fops);
 
 	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
 				&data->trace_cpu, cpu, &tracing_entries_fops);
-- 
cgit v1.2.3-70-g09d2


From 0bc392ee46d0fd8e6b678457ef71f074f19a03c5 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:26:06 +0200
Subject: tracing: Change tracing_entries_fops to rely on tracing_get_cpu()

tracing_open_generic_tc() is racy, the memory inode->i_private
points to can be already freed.

1. Change its last user, tracing_entries_fops, to use
   tracing_*_generic_tr() instead.

2. Change debugfs_create_file("buffer_size_kb", data) callers
   to pass "data = tr".

3. Change tracing_entries_read() and tracing_entries_write() to
   use tracing_get_cpu().

4. Kill the no longer used tracing_open_generic_tc() and
   tracing_release_generic_tc().

Link: http://lkml.kernel.org/r/20130723152606.GA23730@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 49 ++++++++++++-------------------------------------
 1 file changed, 12 insertions(+), 37 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e29dc8f69aa..68b46851666 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2984,23 +2984,6 @@ static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int tracing_open_generic_tc(struct inode *inode, struct file *filp)
-{
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
-
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
-
-	filp->private_data = inode->i_private;
-
-	return 0;
-	
-}
-
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
@@ -3054,15 +3037,6 @@ static int tracing_release_generic_tr(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tc(struct inode *inode, struct file *file)
-{
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
-
-	trace_array_put(tr);
-	return 0;
-}
-
 static int tracing_single_release_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -4382,15 +4356,16 @@ static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
-	struct trace_array *tr = tc->tr;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
+	int cpu = tracing_get_cpu(inode);
 	char buf[64];
 	int r = 0;
 	ssize_t ret;
 
 	mutex_lock(&trace_types_lock);
 
-	if (tc->cpu == RING_BUFFER_ALL_CPUS) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		int cpu, buf_size_same;
 		unsigned long size;
 
@@ -4417,7 +4392,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
 		} else
 			r = sprintf(buf, "X\n");
 	} else
-		r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
+		r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -4429,7 +4404,8 @@ static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
-	struct trace_cpu *tc = filp->private_data;
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
 	unsigned long val;
 	int ret;
 
@@ -4443,8 +4419,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 
 	/* value is in KB */
 	val <<= 10;
-
-	ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
+	ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode));
 	if (ret < 0)
 		return ret;
 
@@ -4892,11 +4867,11 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-	.open		= tracing_open_generic_tc,
+	.open		= tracing_open_generic_tr,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
 	.llseek		= generic_file_llseek,
-	.release	= tracing_release_generic_tc,
+	.release	= tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_total_entries_fops = {
@@ -5580,7 +5555,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 				tr, cpu, &tracing_stats_fops);
 
 	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
-				&data->trace_cpu, cpu, &tracing_entries_fops);
+				tr, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_cpu_file("snapshot", 0644, d_cpu,
@@ -6156,7 +6131,7 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			  tr, &tracing_pipe_fops);
 
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_entries_fops);
+			  tr, &tracing_entries_fops);
 
 	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
 			  tr, &tracing_total_entries_fops);
-- 
cgit v1.2.3-70-g09d2


From 6484c71cbc170634fa131b6d022d86d61686b88b Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:26:10 +0200
Subject: tracing: Change tracing_fops/snapshot_fops to rely on
 tracing_get_cpu()

tracing_open() and tracing_snapshot_open() are racy, the memory
inode->i_private points to can be already freed.

Convert these last users of "inode->i_private == trace_cpu" to
use "i_private = trace_array" and rely on tracing_get_cpu().

v2: incorporate the fix from Steven, tracing_release() must not
    blindly dereference file->private_data unless we know that
    the file was opened for reading.

Link: http://lkml.kernel.org/r/20130723152610.GA23737@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 50 ++++++++++++++++++++++----------------------------
 1 file changed, 22 insertions(+), 28 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68b46851666..dd7780ddde0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2862,9 +2862,9 @@ static const struct seq_operations tracer_seq_ops = {
 };
 
 static struct trace_iterator *
-__tracing_open(struct trace_array *tr, struct trace_cpu *tc,
-	       struct inode *inode, struct file *file, bool snapshot)
+__tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int cpu;
 
@@ -2905,8 +2905,8 @@ __tracing_open(struct trace_array *tr, struct trace_cpu *tc,
 		iter->trace_buffer = &tr->trace_buffer;
 	iter->snapshot = snapshot;
 	iter->pos = -1;
+	iter->cpu_file = tracing_get_cpu(inode);
 	mutex_init(&iter->mutex);
-	iter->cpu_file = tc->cpu;
 
 	/* Notify the tracer early; before we stop tracing. */
 	if (iter->trace && iter->trace->open)
@@ -2986,22 +2986,18 @@ static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 
 static int tracing_release(struct inode *inode, struct file *file)
 {
+	struct trace_array *tr = inode->i_private;
 	struct seq_file *m = file->private_data;
 	struct trace_iterator *iter;
-	struct trace_array *tr;
 	int cpu;
 
-	/* Writes do not use seq_file, need to grab tr from inode */
 	if (!(file->f_mode & FMODE_READ)) {
-		struct trace_cpu *tc = inode->i_private;
-
-		trace_array_put(tc->tr);
+		trace_array_put(tr);
 		return 0;
 	}
 
+	/* Writes do not use seq_file */
 	iter = m->private;
-	tr = iter->tr;
-
 	mutex_lock(&trace_types_lock);
 
 	for_each_tracing_cpu(cpu) {
@@ -3048,8 +3044,7 @@ static int tracing_single_release_tr(struct inode *inode, struct file *file)
 
 static int tracing_open(struct inode *inode, struct file *file)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	int ret = 0;
 
@@ -3057,16 +3052,17 @@ static int tracing_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	/* If this file was open for write, then erase contents */
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC)) {
-		if (tc->cpu == RING_BUFFER_ALL_CPUS)
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		int cpu = tracing_get_cpu(inode);
+
+		if (cpu == RING_BUFFER_ALL_CPUS)
 			tracing_reset_online_cpus(&tr->trace_buffer);
 		else
-			tracing_reset(&tr->trace_buffer, tc->cpu);
+			tracing_reset(&tr->trace_buffer, cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(tr, tc, inode, file, false);
+		iter = __tracing_open(inode, file, false);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
@@ -4680,8 +4676,7 @@ struct ftrace_buffer_info {
 #ifdef CONFIG_TRACER_SNAPSHOT
 static int tracing_snapshot_open(struct inode *inode, struct file *file)
 {
-	struct trace_cpu *tc = inode->i_private;
-	struct trace_array *tr = tc->tr;
+	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	struct seq_file *m;
 	int ret = 0;
@@ -4690,7 +4685,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(tr, tc, inode, file, true);
+		iter = __tracing_open(inode, file, true);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 	} else {
@@ -4707,8 +4702,8 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 		ret = 0;
 
 		iter->tr = tr;
-		iter->trace_buffer = &tc->tr->max_buffer;
-		iter->cpu_file = tc->cpu;
+		iter->trace_buffer = &tr->max_buffer;
+		iter->cpu_file = tracing_get_cpu(inode);
 		m->private = iter;
 		file->private_data = m;
 	}
@@ -5525,7 +5520,6 @@ trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
 static void
 tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 {
-	struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
 	struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
 	struct dentry *d_cpu;
 	char cpu_dir[30]; /* 30 characters should be more than enough */
@@ -5546,7 +5540,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 
 	/* per cpu trace */
 	trace_create_cpu_file("trace", 0644, d_cpu,
-				&data->trace_cpu, cpu, &tracing_fops);
+				tr, cpu, &tracing_fops);
 
 	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
 				tr, cpu, &tracing_buffers_fops);
@@ -5559,7 +5553,7 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_cpu_file("snapshot", 0644, d_cpu,
-				&data->trace_cpu, cpu, &snapshot_fops);
+				tr, cpu, &snapshot_fops);
 
 	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
 				tr, cpu, &snapshot_raw_fops);
@@ -6125,7 +6119,7 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			  tr, &tracing_iter_fops);
 
 	trace_create_file("trace", 0644, d_tracer,
-			(void *)&tr->trace_cpu, &tracing_fops);
+			  tr, &tracing_fops);
 
 	trace_create_file("trace_pipe", 0444, d_tracer,
 			  tr, &tracing_pipe_fops);
@@ -6146,11 +6140,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 			  &trace_clock_fops);
 
 	trace_create_file("tracing_on", 0644, d_tracer,
-			    tr, &rb_simple_fops);
+			  tr, &rb_simple_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_file("snapshot", 0644, d_tracer,
-			  (void *)&tr->trace_cpu, &snapshot_fops);
+			  tr, &snapshot_fops);
 #endif
 
 	for_each_tracing_cpu(cpu)
-- 
cgit v1.2.3-70-g09d2


From 9c01fe4593db123c5a72dc36f0400f776e92c954 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jul 2013 17:26:13 +0200
Subject: tracing: Kill trace_cpu struct/members

After the previous changes trace_array_cpu->trace_cpu and
trace_array->trace_cpu becomes write-only. Remove these members
and kill "struct trace_cpu" as well.

As a side effect this also removes memset(per_cpu_memory, 0).
It was not needed, alloc_percpu() returns zero-filled memory.

Link: http://lkml.kernel.org/r/20130723152613.GA23741@redhat.com

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 21 ---------------------
 kernel/trace/trace.h |  8 --------
 2 files changed, 29 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dd7780ddde0..69cba470ea9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5865,17 +5865,6 @@ struct dentry *trace_instance_dir;
 static void
 init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
 
-static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf)
-{
-	int cpu;
-
-	for_each_tracing_cpu(cpu) {
-		memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu));
-		per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu;
-		per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr;
-	}
-}
-
 static int
 allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
 {
@@ -5893,8 +5882,6 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 		return -ENOMEM;
 	}
 
-	init_trace_buffers(tr, buf);
-
 	/* Allocate the first page for all buffers */
 	set_buffer_entries(&tr->trace_buffer,
 			   ring_buffer_size(tr->trace_buffer.buffer, 0));
@@ -5961,10 +5948,6 @@ static int new_instance_create(const char *name)
 	if (allocate_trace_buffers(tr, trace_buf_size) < 0)
 		goto out_free_tr;
 
-	/* Holder for file callbacks */
-	tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-	tr->trace_cpu.tr = tr;
-
 	tr->dir = debugfs_create_dir(name, trace_instance_dir);
 	if (!tr->dir)
 		goto out_free_tr;
@@ -6438,10 +6421,6 @@ __init static int tracer_alloc_buffers(void)
 
 	global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
 
-	/* Holder for file callbacks */
-	global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
-	global_trace.trace_cpu.tr = &global_trace;
-
 	INIT_LIST_HEAD(&global_trace.systems);
 	INIT_LIST_HEAD(&global_trace.events);
 	list_add(&global_trace.list, &ftrace_trace_arrays);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e7d643b8a90..afaae41b0a0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -130,19 +130,12 @@ enum trace_flag_type {
 
 struct trace_array;
 
-struct trace_cpu {
-	struct trace_array	*tr;
-	struct dentry		*dir;
-	int			cpu;
-};
-
 /*
  * The CPU trace array - it consists of thousands of trace entries
  * plus some other descriptor data: (for example which task started
  * the trace, etc.)
  */
 struct trace_array_cpu {
-	struct trace_cpu	trace_cpu;
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
@@ -196,7 +189,6 @@ struct trace_array {
 	bool			allocated_snapshot;
 #endif
 	int			buffer_disabled;
-	struct trace_cpu	trace_cpu;	/* place holder */
 #ifdef CONFIG_FTRACE_SYSCALLS
 	int			sys_refcount_enter;
 	int			sys_refcount_exit;
-- 
cgit v1.2.3-70-g09d2


From 195a8afc7ac962f8da795549fe38e825f1372b0d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 23 Jul 2013 22:06:15 -0400
Subject: ftrace: Add check for NULL regs if ops has SAVE_REGS set

If a ftrace ops is registered with the SAVE_REGS flag set, and there's
already a ops registered to one of its functions but without the
SAVE_REGS flag, there's a small race window where the SAVE_REGS ops gets
added to the list of callbacks to call for that function before the
callback trampoline gets set to save the regs.

The problem is, the function is not currently saving regs, which opens
a small race window where the ops that is expecting regs to be passed
to it, wont. This can cause a crash if the callback were to reference
the regs, as the SAVE_REGS guarantees that regs will be set.

To fix this, we add a check in the loop case where it checks if the ops
has the SAVE_REGS flag set, and if so, it will ignore it if regs is
not set.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 67708f46baa..8ce9eefc5bb 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1441,12 +1441,22 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
  * the hashes are freed with call_rcu_sched().
  */
 static int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
 	struct ftrace_hash *filter_hash;
 	struct ftrace_hash *notrace_hash;
 	int ret;
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	/*
+	 * There's a small race when adding ops that the ftrace handler
+	 * that wants regs, may be called without them. We can not
+	 * allow that handler to be called if regs is NULL.
+	 */
+	if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS))
+		return 0;
+#endif
+
 	filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
 	notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
 
@@ -4218,7 +4228,7 @@ static inline void ftrace_startup_enable(int command) { }
 # define ftrace_shutdown_sysctl()	do { } while (0)
 
 static inline int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
 	return 1;
 }
@@ -4241,7 +4251,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	do_for_each_ftrace_op(op, ftrace_control_list) {
 		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
 		    !ftrace_function_local_disabled(op) &&
-		    ftrace_ops_test(op, ip))
+		    ftrace_ops_test(op, ip, regs))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
 	trace_recursion_clear(TRACE_CONTROL_BIT);
@@ -4274,7 +4284,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	 */
 	preempt_disable_notrace();
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (ftrace_ops_test(op, ip))
+		if (ftrace_ops_test(op, ip, regs))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
 	preempt_enable_notrace();
-- 
cgit v1.2.3-70-g09d2


From 09d8091c024ec88d1541d93eb8ddb2bd5cf10c39 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 23 Jul 2013 22:21:59 -0400
Subject: tracing: Remove locking trace_types_lock from
 tracing_reset_all_online_cpus()

Commit a82274151af "tracing: Protect ftrace_trace_arrays list in trace_events.c"
added taking the trace_types_lock mutex in trace_events.c as there were
several locations that needed it for protection. Unfortunately, it also
encapsulated a call to tracing_reset_all_online_cpus() which also takes
the trace_types_lock, causing a deadlock.

This happens when a module has tracepoints and has been traced. When the
module is removed, the trace events module notifier will grab the
trace_types_lock, do a bunch of clean ups, and also clears the buffer
by calling tracing_reset_all_online_cpus. This doesn't happen often
which explains why it wasn't caught right away.

Commit a82274151af was marked for stable, which means this must be
sent to stable too.

Link: http://lkml.kernel.org/r/51EEC646.7070306@broadcom.com

Reported-by: Arend van Spril <arend@broadcom.com>
Tested-by: Arend van Spriel <arend@broadcom.com>
Cc: Alexander Z Lam <azl@google.com>
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Cc: David Sharp <dhsharp@google.com>
Cc: stable@vger.kernel.org # 3.10
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 69cba470ea9..882ec1dd151 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1224,18 +1224,17 @@ void tracing_reset_current(int cpu)
 	tracing_reset(&global_trace.trace_buffer, cpu);
 }
 
+/* Must have trace_types_lock held */
 void tracing_reset_all_online_cpus(void)
 {
 	struct trace_array *tr;
 
-	mutex_lock(&trace_types_lock);
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
 		tracing_reset_online_cpus(&tr->trace_buffer);
 #ifdef CONFIG_TRACER_MAX_TRACE
 		tracing_reset_online_cpus(&tr->max_buffer);
 #endif
 	}
-	mutex_unlock(&trace_types_lock);
 }
 
 #define SAVED_CMDLINES 128
-- 
cgit v1.2.3-70-g09d2