[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190215181038.GK5784@redhat.com>
Date: Fri, 15 Feb 2019 16:10:38 -0200
From: Arnaldo Carvalho de Melo <acme@...hat.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
jolsa@...hat.com, Mansour Alharthi <malharthi9@...ech.edu>,
acme@...nel.org
Subject: Re: [PATCH v0 1/2] perf: Copy parent's address filter offsets on
clone
Em Fri, Feb 15, 2019 at 01:56:54PM +0200, Alexander Shishkin escreveu:
> When a child event is allocated in the inherit_event() path, the VMA
> based filter offsets are not copied from the parent, even though the
> address space mapping of the new task remains the same, which leads
> to no trace for the new task until exec.
Peter, I'm processing this one, ok? Ack?
- Arnaldo
> Signed-off-by: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
> Fixes: 375637bc5249 ("perf/core: Introduce address range filtering")
> Reported-by: Mansour Alharthi <malharthi9@...ech.edu>
> ---
> kernel/events/core.c | 15 +++++++++++++++
> 1 file changed, 15 insertions(+)
>
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 5aeb4c74fb99..2d89efc0a3e0 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -1255,6 +1255,7 @@ static void put_ctx(struct perf_event_context *ctx)
> * perf_event_context::lock
> * perf_event::mmap_mutex
> * mmap_sem
> + * perf_addr_filters_head::lock
> *
> * cpu_hotplug_lock
> * pmus_lock
> @@ -10312,6 +10313,20 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
> goto err_per_task;
> }
>
> + /*
> + * Clone the parent's vma offsets: they are valid until exec()
> + * even if the mm is not shared with the parent.
> + */
> + if (event->parent) {
> + struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
> +
> + raw_spin_lock_irq(&ifh->lock);
> + memcpy(event->addr_filters_offs,
> + event->parent->addr_filters_offs,
> + pmu->nr_addr_filters * sizeof(unsigned long));
> + raw_spin_unlock_irq(&ifh->lock);
> + }
> +
> /* force hw sync on the address filters */
> event->addr_filters_gen = 1;
> }
> --
> 2.20.1
Powered by blists - more mailing lists