提交 b84fbc9f 编写于 作者: P Peter Zijlstra 提交者: Ingo Molnar

perf_counter: Push inherit into perf_counter_alloc()

Teach perf_counter_alloc() about inheritance so that we can
optimize the inherit path in the next patch.

Remove the child_counter->atrr.inherit = 1 line because the
only way to get there is if parent_counter->attr.inherit == 1
and we copy the attrs.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
上级 f29ac756
......@@ -3568,6 +3568,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
int cpu,
struct perf_counter_context *ctx,
struct perf_counter *group_leader,
struct perf_counter *parent_counter,
gfp_t gfpflags)
{
const struct pmu *pmu;
......@@ -3603,6 +3604,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
counter->ctx = ctx;
counter->oncpu = -1;
counter->parent = parent_counter;
counter->ns = get_pid_ns(current->nsproxy->pid_ns);
counter->id = atomic64_inc_return(&perf_counter_id);
......@@ -3827,7 +3830,7 @@ SYSCALL_DEFINE5(perf_counter_open,
}
counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
GFP_KERNEL);
NULL, GFP_KERNEL);
ret = PTR_ERR(counter);
if (IS_ERR(counter))
goto err_put_context;
......@@ -3893,7 +3896,8 @@ inherit_counter(struct perf_counter *parent_counter,
child_counter = perf_counter_alloc(&parent_counter->attr,
parent_counter->cpu, child_ctx,
group_leader, GFP_KERNEL);
group_leader, parent_counter,
GFP_KERNEL);
if (IS_ERR(child_counter))
return child_counter;
get_ctx(child_ctx);
......@@ -3916,12 +3920,6 @@ inherit_counter(struct perf_counter *parent_counter,
*/
add_counter_to_ctx(child_counter, child_ctx);
child_counter->parent = parent_counter;
/*
* inherit into child's child as well:
*/
child_counter->attr.inherit = 1;
/*
* Get a reference to the parent filp - we will fput it
* when the child counter exits. This is safe to do because
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册