Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth via sysctl

From: Peter Zijlstra
Date: Thu Apr 21 2016 - 06:49:59 EST


On Wed, Apr 20, 2016 at 07:47:30PM -0300, Arnaldo Carvalho de Melo wrote:
> The default remains 127, which is good for most cases, and not even hit
> most of the time, but then for some cases, as reported by Brendan, 1024+
> deep frames are appearing on the radar for things like groovy, ruby.

yea gawds ;-)



> index 343c22f5e867..1390747b2195 100644
> --- a/kernel/events/callchain.c
> +++ b/kernel/events/callchain.c
> @@ -18,6 +18,14 @@ struct callchain_cpus_entries {
> struct perf_callchain_entry *cpu_entries[0];
> };
>
> +int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
> +
> +static size_t perf_callchain_entry__sizeof(void)
> +{
> + return sizeof(struct perf_callchain_entry) +
> + sizeof(__u64) * sysctl_perf_event_max_stack;
> +}
> +
> static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
> static atomic_t nr_callchain_events;
> static DEFINE_MUTEX(callchain_mutex);
> @@ -73,7 +81,7 @@ static int alloc_callchain_buffers(void)
> if (!entries)
> return -ENOMEM;
>
> - size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
> + size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
>
> for_each_possible_cpu(cpu) {
> entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,

And this alloc _will_ fail if you put in a decent sized value..

Should we put in a dmesg WARN if this alloc fails and
perf_event_max_stack is 'large' ?

> @@ -215,3 +223,25 @@ exit_put:
>
> return entry;
> }
> +
> +int perf_event_max_stack_handler(struct ctl_table *table, int write,
> + void __user *buffer, size_t *lenp, loff_t *ppos)
> +{
> + int new_value = sysctl_perf_event_max_stack, ret;
> + struct ctl_table new_table = *table;
> +
> + new_table.data = &new_value;

cute :-)

> + ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos);
> + if (ret || !write)
> + return ret;
> +
> + mutex_lock(&callchain_mutex);
> + if (atomic_read(&nr_callchain_events))
> + ret = -EBUSY;
> + else
> + sysctl_perf_event_max_stack = new_value;
> +
> + mutex_unlock(&callchain_mutex);
> +
> + return ret;
> +}