perf_counter: Separate out attr->type from attr->config
Counter type is a frequently used value and we do a lot of
bit juggling by encoding and decoding it from attr->config.
Clean this up by creating a separate attr->type field.
Also clean up the various similarly complex user-space bits
all around counter attribute management.
The net improvement is significant, and it will be easier
to add a new major type (which is what triggered this cleanup).
(This changes the ABI, all tools are adapted.)
(PowerPC build-tested.)
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 47c92fb..75ae767 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -3091,14 +3091,12 @@
enum perf_event_types type,
u32 event, struct pt_regs *regs)
{
- u64 event_config;
-
- event_config = ((u64) type << PERF_COUNTER_TYPE_SHIFT) | event;
-
if (!perf_swcounter_is_counting(counter))
return 0;
- if (counter->attr.config != event_config)
+ if (counter->attr.type != type)
+ return 0;
+ if (counter->attr.config != event)
return 0;
if (regs) {
@@ -3403,7 +3401,7 @@
* to be kernel events, and page faults are never hypervisor
* events.
*/
- switch (perf_event_id(&counter->attr)) {
+ switch (counter->attr.config) {
case PERF_COUNT_CPU_CLOCK:
pmu = &perf_ops_cpu_clock;
@@ -3496,12 +3494,12 @@
if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
goto done;
- if (perf_event_raw(attr)) {
+ if (attr->type == PERF_TYPE_RAW) {
pmu = hw_perf_counter_init(counter);
goto done;
}
- switch (perf_event_type(attr)) {
+ switch (attr->type) {
case PERF_TYPE_HARDWARE:
pmu = hw_perf_counter_init(counter);
break;