Re: [PATCH] ring-buffer: Add barrire in rb_move_tail

[lijiazi <jqqlijiazi@gmail.com>]

On Wed, Sep 28, 2022 at 04:29:08PM -0400, Steven Rostedt wrote:
> On Wed, 28 Sep 2022 10:59:35 -0400
> Steven Rostedt <rostedt@goodmis.org> wrote:
> 
> > > Will reply with an updated patch.  
> > 
> > Can you try this patch?
> 
> Actually, that failed my testing (for other reasons), can you try this one?
> 
Sure, thank you.
> -- Steve
> 
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index 3046deacf7b3..46b6f4107428 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -2648,6 +2648,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
>  		/* Mark the rest of the page with padding */
>  		rb_event_set_padding(event);
>  
> +		/* Make sure the padding is visible before the write update */
> +		smp_wmb();
> +
>  		/* Set the write back to the previous setting */
>  		local_sub(length, &tail_page->write);
>  		return;
> @@ -2659,6 +2662,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
>  	/* time delta must be non zero */
>  	event->time_delta = 1;
>  
> +	/* Make sure the padding is visible before the tail_page->write update */
> +	smp_wmb();
> +
>  	/* Set write to end of buffer */
>  	length = (tail + length) - BUF_PAGE_SIZE;
>  	local_sub(length, &tail_page->write);
> @@ -4627,6 +4633,29 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
>  	arch_spin_unlock(&cpu_buffer->lock);
>  	local_irq_restore(flags);
>  
> +	/* The writer has preempt disable, wait for it. But not forever */
> +        for (nr_loops = 0; nr_loops < 1000; nr_loops++) {
> +		/* If the write is past the end of page, a writer is still updating it */
> +		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
> +			break;
> +
> +		udelay(1);
> +
> +		/* Get the latest version of the reader write value */
> +		smp_rmb();
> +	}
> +
> +	/* The writer is not moving forward? Something is wrong */
> +	if (RB_WARN_ON(cpu_buffer, nr_loops == 1000))
> +		reader = NULL;
> +
> +	/*
> +	 * Make sure we see any padding after the write update
> +	 * (see rb_reset_tail())
> +	 */
> +	smp_rmb();
> +
> +
>  	return reader;
>  }
>