Re: [PATCH V9 1/6] tracing: add a possibility of exporting function trace to other places instead of ring buffer only

[Chunyan Zhang]

Hi Steve,

Actually I had been keeping the idea that we would need to export most
kinds of traces rather than function trace only to somewhere else, say
STM, that's also why I made STM_SOURCE_FTRACE depending on TRACING
which was later changed to FUNCTION_TRACER according to you advice.

Thanks,
Chunyan

On 23 November 2016 at 10:27, Chunyan Zhang <zhang.chunyan@xxxxxxxxxx> wrote:
> On 23 November 2016 at 06:39, Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:
>> On Mon, 21 Nov 2016 15:57:18 +0800
>> Chunyan Zhang <zhang.chunyan@xxxxxxxxxx> wrote:
>>
>>> Currently Function traces can be only exported to ring buffer, this
>>> patch added trace_export concept which can process traces and export
>>> them to a registered destination as an addition to the current only
>>> one output of Ftrace - i.e. ring buffer.
>>>
>>> In this way, if we want Function traces to be sent to other destination
>>> rather than ring buffer only, we just need to register a new trace_export
>>> and implement its own .write() function for writing traces to storage.
>>>
>>> With this patch, only Function trace (trace type is TRACE_FN)
>>> is supported.
>>>
>>> Signed-off-by: Chunyan Zhang <zhang.chunyan@xxxxxxxxxx>
>>> ---
>>>  include/linux/trace.h |  28 +++++++++++
>>>  kernel/trace/trace.c  | 129 +++++++++++++++++++++++++++++++++++++++++++++++++-
>>>  2 files changed, 156 insertions(+), 1 deletion(-)
>>>  create mode 100644 include/linux/trace.h
>>>
>>> diff --git a/include/linux/trace.h b/include/linux/trace.h
>>> new file mode 100644
>>> index 0000000..9330a58
>>> --- /dev/null
>>> +++ b/include/linux/trace.h
>>> @@ -0,0 +1,28 @@
>>> +#ifndef _LINUX_TRACE_H
>>> +#define _LINUX_TRACE_H
>>> +
>>> +#ifdef CONFIG_TRACING
>>> +/*
>>> + * The trace export - an export of Ftrace output. The trace_export
>>> + * can process traces and export them to a registered destination as
>>> + * an addition to the current only output of Ftrace - i.e. ring buffer.
>>> + *
>>> + * If you want traces to be sent to some other place rather than ring
>>> + * buffer only, just need to register a new trace_export and implement
>>> + * its own .write() function for writing traces to the storage.
>>> + *
>>> + * next              - pointer to the next trace_export
>>> + * write     - copy traces which have been delt with ->commit() to
>>> + *             the destination
>>> + */
>>> +struct trace_export {
>>> +     struct trace_export __rcu       *next;
>>> +     void (*write)(const void *, unsigned int);
>>> +};
>>> +
>>> +int register_ftrace_export(struct trace_export *export);
>>> +int unregister_ftrace_export(struct trace_export *export);
>>> +
>>> +#endif       /* CONFIG_TRACING */
>>> +
>>> +#endif       /* _LINUX_TRACE_H */
>>> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
>>> index 8696ce6..038291d 100644
>>> --- a/kernel/trace/trace.c
>>> +++ b/kernel/trace/trace.c
>>> @@ -40,6 +40,7 @@
>>>  #include <linux/poll.h>
>>>  #include <linux/nmi.h>
>>>  #include <linux/fs.h>
>>> +#include <linux/trace.h>
>>>  #include <linux/sched/rt.h>
>>>
>>>  #include "trace.h"
>>> @@ -2128,6 +2129,129 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
>>>       ftrace_trace_userstack(buffer, flags, pc);
>>>  }
>>>
>>> +static void
>>> +trace_process_export(struct trace_export *export,
>>> +            struct ring_buffer_event *event)
>>> +{
>>> +     struct trace_entry *entry;
>>> +     unsigned int size = 0;
>>> +
>>> +     entry = ring_buffer_event_data(event);
>>> +     size = ring_buffer_event_length(event);
>>> +     export->write(entry, size);
>>> +}
>>> +
>>> +static DEFINE_MUTEX(ftrace_export_lock);
>>> +
>>> +static struct trace_export __rcu *ftrace_exports_list __read_mostly;
>>> +
>>> +static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled);
>>> +
>>> +static inline void ftrace_exports_enable(void)
>>> +{
>>> +     static_branch_enable(&ftrace_exports_enabled);
>>> +}
>>> +
>>> +static inline void ftrace_exports_disable(void)
>>> +{
>>> +     static_branch_disable(&ftrace_exports_enabled);
>>> +}
>>> +
>>> +void ftrace_exports(struct ring_buffer_event *event)
>>
>> I'm currently testing the patches, but is there a reason that
>> ftrace_exports() is not static?
>
> At present  ftrace_exports() is only used by function trace though,
> but I hope it can be used by other traces when it needed.
> So I didn't mark it with static, but if you think it should better be
> static for the time being, I can revise that.
>
> Thanks,
> Chunyan
>
>
>>
>> -- Steve
>>
>>> +{
>>> +     struct trace_export *export;
>>> +
>>> +     preempt_disable_notrace();
>>> +
>>> +     export = rcu_dereference_raw_notrace(ftrace_exports_list);
>>> +     while (export) {
>>> +             trace_process_export(export, event);
>>> +             export = rcu_dereference_raw_notrace(export->next);
>>> +     }
>>> +
>>> +     preempt_enable_notrace();
>>> +}
>>> +
>>> +static inline void
>>> +add_trace_export(struct trace_export **list, struct trace_export *export)
>>> +{
>>> +     rcu_assign_pointer(export->next, *list);
>>> +     /*
>>> +      * We are entering export into the list but another
>>> +      * CPU might be walking that list. We need to make sure
>>> +      * the export->next pointer is valid before another CPU sees
>>> +      * the export pointer included into the list.
>>> +      */
>>> +     rcu_assign_pointer(*list, export);
>>> +}
>>> +
>>> +static inline int
>>> +rm_trace_export(struct trace_export **list, struct trace_export *export)
>>> +{
>>> +     struct trace_export **p;
>>> +
>>> +     for (p = list; *p != NULL; p = &(*p)->next)
>>> +             if (*p == export)
>>> +                     break;
>>> +
>>> +     if (*p != export)
>>> +             return -1;
>>> +
>>> +     rcu_assign_pointer(*p, (*p)->next);
>>> +
>>> +     return 0;
>>> +}
>>> +
>>> +static inline void
>>> +add_ftrace_export(struct trace_export **list, struct trace_export *export)
>>> +{
>>> +     if (*list == NULL)
>>> +             ftrace_exports_enable();
>>> +
>>> +     add_trace_export(list, export);
>>> +}
>>> +
>>> +static inline int
>>> +rm_ftrace_export(struct trace_export **list, struct trace_export *export)
>>> +{
>>> +     int ret;
>>> +
>>> +     ret = rm_trace_export(list, export);
>>> +     if (*list == NULL)
>>> +             ftrace_exports_disable();
>>> +
>>> +     return ret;
>>> +}
>>> +
>>> +int register_ftrace_export(struct trace_export *export)
>>> +{
>>> +     if (WARN_ON_ONCE(!export->write))
>>> +             return -1;
>>> +
>>> +     mutex_lock(&ftrace_export_lock);
>>> +
>>> +     add_ftrace_export(&ftrace_exports_list, export);
>>> +
>>> +     mutex_unlock(&ftrace_export_lock);
>>> +
>>> +     return 0;
>>> +}
>>> +EXPORT_SYMBOL_GPL(register_ftrace_export);
>>> +
>>> +int unregister_ftrace_export(struct trace_export *export)
>>> +{
>>> +     int ret;
>>> +
>>> +     mutex_lock(&ftrace_export_lock);
>>> +
>>> +     ret = rm_ftrace_export(&ftrace_exports_list, export);
>>> +
>>> +     mutex_unlock(&ftrace_export_lock);
>>> +
>>> +     return ret;
>>> +}
>>> +EXPORT_SYMBOL_GPL(unregister_ftrace_export);
>>> +
>>>  void
>>>  trace_function(struct trace_array *tr,
>>>              unsigned long ip, unsigned long parent_ip, unsigned long flags,
>>> @@ -2146,8 +2270,11 @@ trace_function(struct trace_array *tr,
>>>       entry->ip                       = ip;
>>>       entry->parent_ip                = parent_ip;
>>>
>>> -     if (!call_filter_check_discard(call, entry, buffer, event))
>>> +     if (!call_filter_check_discard(call, entry, buffer, event)) {
>>> +             if (static_branch_unlikely(&ftrace_exports_enabled))
>>> +                     ftrace_exports(event);
>>>               __buffer_unlock_commit(buffer, event);
>>> +     }
>>>  }
>>>
>>>  #ifdef CONFIG_STACKTRACE
>>