tracing: Failed to create system directory

Running the following:

 # cd /sys/kernel/debug/tracing
 # echo p:i do_sys_open > kprobe_events
 # echo p:j schedule >> kprobe_events
 # cat kprobe_events
p:kprobes/i do_sys_open
p:kprobes/j schedule
 # echo p:i do_sys_open >> kprobe_events
 # cat kprobe_events
p:kprobes/j schedule
p:kprobes/i do_sys_open
 # ls /sys/kernel/debug/tracing/events/kprobes/
enable  filter  j

Notice that the 'i' is missing from the kprobes directory.

The console produces:

"Failed to create system directory kprobes"

This is because kprobes passes in a allocated name for the system
and the ftrace event subsystem saves off that name instead of creating
a duplicate for it. But the kprobes may free the system name making
the pointer to it invalid.

This bug was introduced by 92edca073c37 "tracing: Use direct field, type
and system names" which switched from using kstrdup() on the system name
in favor of just keeping apointer to it, as the internal ftrace event
system names are static and exist for the life of the computer being booted.

Instead of reverting back to duplicating system names again, we can use
core_kernel_data() to determine if the passed in name was allocated or
static. Then use the MSB of the ref_count to be a flag to keep track if
the name was allocated or not. Then we can still save from having to duplicate
strings that will always exist, but still copy the ones that may be freed.

Cc: stable@vger.kernel.org # 3.10
Reported-by: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Reported-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f57b01574a30f5237efa63b16cf44c8e91ca4fbd..903a0bf2685ec767b82a670d58af09d53aaa9e48 100644 (file)
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -41,6 +41,23 @@ static LIST_HEAD(ftrace_common_fields);
 static struct kmem_cache *field_cachep;
 static struct kmem_cache *file_cachep;
 
+#define SYSTEM_FL_FREE_NAME            (1 << 31)
+
+static inline int system_refcount(struct event_subsystem *system)
+{
+       return system->ref_count & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_inc(struct event_subsystem *system)
+{
+       return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_dec(struct event_subsystem *system)
+{
+       return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME;
+}
+
 /* Double loops, do not use break, only goto's work */
 #define do_for_each_event_file(tr, file)                       \
        list_for_each_entry(tr, &ftrace_trace_arrays, list) {   \
@@ -344,8 +361,8 @@ static void __put_system(struct event_subsystem *system)
 {
        struct event_filter *filter = system->filter;
 
-       WARN_ON_ONCE(system->ref_count == 0);
-       if (--system->ref_count)
+       WARN_ON_ONCE(system_refcount(system) == 0);
+       if (system_refcount_dec(system))
                return;
 
        list_del(&system->list);
@@ -354,13 +371,15 @@ static void __put_system(struct event_subsystem *system)
                kfree(filter->filter_string);
                kfree(filter);
        }
+       if (system->ref_count & SYSTEM_FL_FREE_NAME)
+               kfree(system->name);
        kfree(system);
 }
 
 static void __get_system(struct event_subsystem *system)
 {
-       WARN_ON_ONCE(system->ref_count == 0);
-       system->ref_count++;
+       WARN_ON_ONCE(system_refcount(system) == 0);
+       system_refcount_inc(system);
 }
 
 static void __get_system_dir(struct ftrace_subsystem_dir *dir)
@@ -374,7 +393,7 @@ static void __put_system_dir(struct ftrace_subsystem_dir *dir)
 {
        WARN_ON_ONCE(dir->ref_count == 0);
        /* If the subsystem is about to be freed, the dir must be too */
-       WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1);
+       WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1);
 
        __put_system(dir->subsystem);
        if (!--dir->ref_count)
@@ -1274,7 +1293,15 @@ create_new_subsystem(const char *name)
                return NULL;
 
        system->ref_count = 1;
-       system->name = name;
+
+       /* Only allocate if dynamic (kprobes and modules) */
+       if (!core_kernel_data((unsigned long)name)) {
+               system->ref_count |= SYSTEM_FL_FREE_NAME;
+               system->name = kstrdup(name, GFP_KERNEL);
+               if (!system->name)
+                       goto out_free;
+       } else
+               system->name = name;
 
        system->filter = NULL;
 
@@ -1287,6 +1314,8 @@ create_new_subsystem(const char *name)
        return system;
 
  out_free:
+       if (system->ref_count & SYSTEM_FL_FREE_NAME)
+               kfree(system->name);
        kfree(system);
        return NULL;
 }