lkml.org 
[lkml]   [2016]   [Apr]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth via sysctl
Em Mon, Apr 25, 2016 at 01:27:06PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Apr 25, 2016 at 01:14:25PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Fri, Apr 22, 2016 at 03:18:08PM -0700, Alexei Starovoitov escreveu:
> > > right... and looking into it further, realized that the patch is broken,
> > > since get_callchain_entry() is doing:
> > > return &entries->cpu_entries[cpu][*rctx];
> > > whereas it should be dynamic offset based on sysctl_perf_event_max_stack*8
> > > So definitely needs another respin.

> struct perf_callchain_entry {
> __u64 nr;
> __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
> };

> But perf_callchain_entry->ip is not a pointer... Got it ;-\

This is what I am building now, a patch on top of the previous, that
will be combined and sent as v3, if I don't find any more funnies:

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 6fe77349fa9d..40657892a7e0 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -20,11 +20,10 @@ struct callchain_cpus_entries {

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;
-}
+#define __perf_callchain_entry_size(entries) \
+ (sizeof(struct perf_callchain_entry) + sizeof(__u64) * entries)
+
+static size_t perf_callchain_entry_size __read_mostly = __perf_callchain_entry_size(PERF_MAX_STACK_DEPTH);

static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
static atomic_t nr_callchain_events;
@@ -81,7 +80,7 @@ static int alloc_callchain_buffers(void)
if (!entries)
return -ENOMEM;

- size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
+ size = perf_callchain_entry_size * PERF_NR_CONTEXTS;

for_each_possible_cpu(cpu) {
entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
@@ -155,7 +154,8 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)

cpu = smp_processor_id();

- return &entries->cpu_entries[cpu][*rctx];
+ return (((void *)&entries->cpu_entries[cpu][0]) +
+ (*rctx * perf_callchain_entry_size));
}

static void
@@ -236,10 +236,12 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write,
return ret;

mutex_lock(&callchain_mutex);
- if (atomic_read(&nr_callchain_events))
+ if (atomic_read(&nr_callchain_events)) {
ret = -EBUSY;
- else
+ } else {
sysctl_perf_event_max_stack = new_value;
+ perf_callchain_entry_size = __perf_callchain_entry_size(new_value);
+ }

mutex_unlock(&callchain_mutex);

\
 
 \ /
  Last update: 2016-04-25 21:41    [W:0.498 / U:0.152 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site