Re: [PATCH RESEND 1/2] tracing: syscall_*regfunc() can race with copy_process()

[Steven Rostedt]

On Wed, 9 Apr 2014 19:05:42 +0200
Oleg Nesterov <oleg@xxxxxxxxxx> wrote:

> syscall_regfunc() and syscall_unregfunc() should set/clear
> TIF_SYSCALL_TRACEPOINT system-wide, but do_each_thread() can race
> with copy_process() and miss the new child which was not added to
> init_task.tasks list yet.
> 
> Change copy_process() to update the child's TIF_SYSCALL_TRACEPOINT
> under tasklist.
> 
> While at it,
> 
> 	- remove _irqsafe from syscall_regfunc/syscall_unregfunc,
> 	  read_lock(tasklist) doesn't need to disable irqs.
> 
> 	- change syscall_unregfunc() to check PF_KTHREAD to skip
> 	  the kernel threads, ->mm != NULL is the common mistake.
> 
> 	  Note: probably this check should be simply removed, needs
> 	  another patch.
> 
> Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
> ---
>  include/trace/syscall.h |   15 +++++++++++++++
>  kernel/fork.c           |    2 ++
>  kernel/tracepoint.c     |   12 +++++-------
>  3 files changed, 22 insertions(+), 7 deletions(-)
> 
> diff --git a/include/trace/syscall.h b/include/trace/syscall.h
> index 84bc419..15a954b 100644
> --- a/include/trace/syscall.h
> +++ b/include/trace/syscall.h
> @@ -4,6 +4,7 @@
>  #include <linux/tracepoint.h>
>  #include <linux/unistd.h>
>  #include <linux/ftrace_event.h>
> +#include <linux/thread_info.h>
>  
>  #include <asm/ptrace.h>
>  
> @@ -31,4 +32,18 @@ struct syscall_metadata {
>  	struct ftrace_event_call *exit_event;
>  };
>  
> +#ifdef CONFIG_TRACEPOINTS
> +static inline void syscall_tracepoint_update(struct task_struct *p)
> +{
> +	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
> +		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
> +	else
> +		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
> +}
> +#else
> +static inline void syscall_tracepoint_update(struct task_struct *p)
> +{
> +}
> +#endif
> +
>  #endif /* _TRACE_SYSCALL_H */
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 1766d32..e463f99 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1472,7 +1472,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
>  
>  	total_forks++;
>  	spin_unlock(&current->sighand->siglock);
> +	syscall_tracepoint_update(p);
>  	write_unlock_irq(&tasklist_lock);
> +

So this looks to be a fix that probably should go to stable?

>  	proc_fork_connector(p);
>  	cgroup_post_fork(p);
>  	if (clone_flags & CLONE_THREAD)
> diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
> index 0c05a45..a16754b 100644
> --- a/kernel/tracepoint.c
> +++ b/kernel/tracepoint.c
> @@ -732,33 +732,31 @@ static int sys_tracepoint_refcount;
>  
>  void syscall_regfunc(void)
>  {
> -	unsigned long flags;
>  	struct task_struct *g, *t;
>  
>  	if (!sys_tracepoint_refcount) {
> -		read_lock_irqsave(&tasklist_lock, flags);
> +		read_lock(&tasklist_lock);
>  		do_each_thread(g, t) {
>  			/* Skip kernel threads. */
> -			if (t->mm)
> +			if (!(t->flags & PF_KTHREAD))
>  				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
>  		} while_each_thread(g, t);
> -		read_unlock_irqrestore(&tasklist_lock, flags);
> +		read_unlock(&tasklist_lock);
>  	}
>  	sys_tracepoint_refcount++;
>  }
>  
>  void syscall_unregfunc(void)
>  {
> -	unsigned long flags;
>  	struct task_struct *g, *t;
>  
>  	sys_tracepoint_refcount--;
>  	if (!sys_tracepoint_refcount) {
> -		read_lock_irqsave(&tasklist_lock, flags);
> +		read_lock(&tasklist_lock);
>  		do_each_thread(g, t) {
>  			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
>  		} while_each_thread(g, t);
> -		read_unlock_irqrestore(&tasklist_lock, flags);
> +		read_unlock(&tasklist_lock);

These changes should be in a separate patch, as they can wait till 3.16.

-- Steve

>  	}
>  }
>  #endif

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/