Re: BUG in "perf: Suppress AUX/OVERWRITE records"?

[Will Deacon <will.deacon@arm.com>]

On Wed, Mar 27, 2019 at 11:17:43AM +0200, Alexander Shishkin wrote:
> Ben Gainey <Ben.Gainey@arm.com> writes:
> 
> >> It was an unintentional side effect that it also
> >> happened to coincide with context switches in the overwrite mode.
> >
> > I'm not using overwrite mode, I'm opening the mmap with PROT_WRITE
> > (i.e. in truncate mode).
> 
> Now I get it. Does the below fix the problem for you?
> 
> From bf52320cce0e74a2c0d987db7bd571f7687b4f4f Mon Sep 17 00:00:00 2001
> From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Date: Wed, 27 Mar 2019 11:05:53 +0200
> Subject: [PATCH] perf: Fix AUX record suppression
> 
> Commit 1627314fb54a33e ("perf: Suppress AUX/OVERWRITE records") has an
> unintended side-effect of also suppressing all AUX records with no flags
> and non-zero size, so all the regular records in the full trace mode.
> This breaks some use cases for people.
> 
> Fix this by restoring "regular" AUX records to their former glory.
> 
> Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Fixes: 1627314fb54a33e ("perf: Suppress AUX/OVERWRITE records")
> Reported-by: Ben Gainey <Ben.Gainey@arm.com>
> CC: stable@vger.kernel.org # v4.20+
> ---
>  kernel/events/ring_buffer.c | 33 +++++++++++++++------------------
>  1 file changed, 15 insertions(+), 18 deletions(-)
> 
> diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
> index 678ccec60d8f..626256dc26c1 100644
> --- a/kernel/events/ring_buffer.c
> +++ b/kernel/events/ring_buffer.c
> @@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
>  		rb->aux_head += size;
>  	}
>  
> -	if (size || handle->aux_flags) {
> -		/*
> -		 * Only send RECORD_AUX if we have something useful to communicate
> -		 *
> -		 * Note: the OVERWRITE records by themselves are not considered
> -		 * useful, as they don't communicate any *new* information,
> -		 * aside from the short-lived offset, that becomes history at
> -		 * the next event sched-in and therefore isn't useful.
> -		 * The userspace that needs to copy out AUX data in overwrite
> -		 * mode should know to use user_page::aux_head for the actual
> -		 * offset. So, from now on we don't output AUX records that
> -		 * have *only* OVERWRITE flag set.
> -		 */
> -
> -		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
> -			perf_event_aux_event(handle->event, aux_head, size,
> -			                     handle->aux_flags);
> -	}
> +	/*
> +	 * Only send RECORD_AUX if we have something useful to communicate
> +	 *
> +	 * Note: the OVERWRITE records by themselves are not considered
> +	 * useful, as they don't communicate any *new* information,
> +	 * aside from the short-lived offset, that becomes history at
> +	 * the next event sched-in and therefore isn't useful.
> +	 * The userspace that needs to copy out AUX data in overwrite
> +	 * mode should know to use user_page::aux_head for the actual
> +	 * offset. So, from now on we don't output AUX records that
> +	 * have *only* OVERWRITE flag set.
> +	 */
> +	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
> +		perf_event_aux_event(handle->event, aux_head, size,
> +				     handle->aux_flags);

Acked-by: Will Deacon <will.deacon@arm.com>

Assuming this will make it into 5.1 as a fix?

Will