On Mon, Jul 17, 2017 at 04:28:38PM +0800, Jin, Yao wrote:
> I'm also waiting for Peter's review comments for this patch update.
Aside from Jiri's comment (which I agree with)
Acked-by: Peter Zijlstra (Intel)
for the first two patches.
On 7/17/2017 4:11 PM, Jiri Olsa wrote:
On Mon, Jul 17, 2017 at 07:06:38PM +0800, Jin Yao wrote:
SNIP
+#define X86_BR_TYPE_MAP_MAX16
+
+static int
+common_branch_type(int type)
+{
+ int i;
+ const int branch_map[X86_BR_TYPE_MAP_MAX] = {
+ PERF_BR_CALL,
On Mon, Jul 17, 2017 at 07:06:38PM +0800, Jin Yao wrote:
SNIP
> +#define X86_BR_TYPE_MAP_MAX 16
> +
> +static int
> +common_branch_type(int type)
> +{
> + int i;
> + const int branch_map[X86_BR_TYPE_MAP_MAX] = {
> + PERF_BR_CALL, /* X86_BR_CALL */
> + PE
Perf already has support for disassembling the branch instruction
and using the branch type for filtering. The patch just records
the branch type in perf_branch_entry.
Before recording, the patch converts the x86 branch type to
common branch type.
Change log
--
v9: Use __ffs() to find fir
4 matches
Mail list logo