[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20210226024818.655494375@goodmis.org>
Date: Thu, 25 Feb 2021 21:47:52 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: linux-kernel@...r.kernel.org
Cc: Ingo Molnar <mingo@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Jacob Wen <jian.w.wen@...cle.com>
Subject: [for-linus][PATCH 1/2] mm, tracing: Fix kmem_cache_free trace event to not print stale
pointers
From: "Steven Rostedt (VMware)" <rostedt@...dmis.org>
The update to kmem_cache_free trace event added printing of the slab name in
the trace event. But it only stores the pointer of the name which will be
printed as a string when the event is read some time in the future. This is
dangerous because the name could be freed in the mean time and when reading
the trace event it would try to dereference the string name by the pointer
to the name that has been freed.
Instead, use the trace event helper macros __string(), __assign_str(), and
__get_str() that are for this very case.
Cc: Jacob Wen <jian.w.wen@...cle.com>
Fixes: 3544de8ee6e4 ("mm, tracing: record slab name for kmem_cache_free()")
Signed-off-by: Steven Rostedt (VMware) <rostedt@...dmis.org>
---
include/trace/events/kmem.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 40845b0d5dad..3a60b6b6db32 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -144,17 +144,17 @@ TRACE_EVENT(kmem_cache_free,
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
- __field( const char *, name )
+ __string( name, name )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
- __entry->name = name;
+ __assign_str(name, name);
),
TP_printk("call_site=%pS ptr=%p name=%s",
- (void *)__entry->call_site, __entry->ptr, __entry->name)
+ (void *)__entry->call_site, __entry->ptr, __get_str(name))
);
TRACE_EVENT(mm_page_free,
--
2.30.0
Powered by blists - more mailing lists