Re: [PATCH] perf_counter: allow and require one-page mmap on counting counters

[Ingo Molnar <mingo@elte.hu>]

* Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:

> On Wed, 2009-03-25 at 19:15 +1100, Paul Mackerras wrote:
> > Impact: bug fix
> > 
> > Currently the mmap code requires that the length of the mmap be at least
> > two pages.  That is fine for sampling counters, but for counting
> > counters the second and subsequent pages are just wasted, since counting
> > counters don't generate events.
> > 
> > This changes the code to require that the mmap be one page in length
> > for counting counters, and applies the existing check to sampling
> > counters.
> 
> Does the below work for you Paul?
> 
> ---
> Subject: perf_counter: allow one-page mmap on counters
> From: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Date: Wed Mar 25 12:44:16 CET 2009
> 
> A brainfart stopped single page mmap()s working. The rest of the code
> should be perfectly fine with not having any data pages.
> 
> Reported-by: Paul Mackerras <paulus@samba.org>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  kernel/perf_counter.c |    6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
> 
> Index: linux-2.6/kernel/perf_counter.c
> ===================================================================
> --- linux-2.6.orig/kernel/perf_counter.c
> +++ linux-2.6/kernel/perf_counter.c
> @@ -1369,7 +1369,11 @@ static int perf_mmap(struct file *file, 
>  	vma_size = vma->vm_end - vma->vm_start;
>  	nr_pages = (vma_size / PAGE_SIZE) - 1;
>  
> -	if (nr_pages == 0 || !is_power_of_2(nr_pages))
> +	/*
> +	 * If we have data pages ensure they're a power-of-two number, so we
> +	 * can do bitmasks instead of modulo.
> +	 */
> +	if (nr_pages != 0 && !is_power_of_2(nr_pages))
>  		return -EINVAL;

Yeah - this is cleaner.

	Ingo