Re: [PATCH v6 01/26] tools headers uapi: Update tools's copy of linux/perf_event.h
From: Jin, Yao
Date: Tue Apr 27 2021 - 21:18:19 EST
Hi Arnaldo,
On 4/28/2021 3:24 AM, Arnaldo Carvalho de Melo wrote:
Em Tue, Apr 27, 2021 at 03:01:14PM +0800, Jin Yao escreveu:
To get the changes in:
Liang Kan's patch
[PATCH V6 21/25] perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
Kan's patch is upstreamed yet but perf/core branch doesn't have it
at this moment. But next perf tool patches need this interface for
hybrid support.
This patch can be removed after Kan's patch is merged in perf/core
branch.
Nope, it is already in tip/perf/core as:
55bcf6ef314ae8ba ("perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE")
Oh, the perf/core mentioned here just means the "perf/core" from acme/linux.git. Sorry, I didn't say
this clearly. I guess it will be merged to acme/linux.git at some window.
And your patch, the one below, shouldn't include the kernel file, i.e. include/uapi/linux/perf_event.h
as tooling only uses the one in tools/include/uapi/linux/perf_event.h.
Yes, my fault. I only need to update the tools/include/uapi/linux/perf_event.h. You have helped me
to update the commit 7ad6382ef375 ("tools headers uapi: Update tools's copy of linux/perf_event.h")
in tmp.perf/core. Thanks so much!
Leave the perf tool build warning there, as soon as both acme/perf/core
and tip/perf/core hit torvalds/master, all gets solved.
So I'm removing it here in addition to updating the commit log message.
Thanks again!
Ah good news, the test builds passed in all my test build containers.
Great! :)
I'll refresh tmp.perf/core once I update these messages, etc. So that we
can continue from there in case you need to respin a v7.
I've seen the patches have been applied in tmp.perf/core now, thanks! If we need v7, we can continue
from tmp.perf/core.
Thanks
Jin Yao
Thanks,
- Arnaldo.
Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
v6:
- No update.
v5:
- Update the commit message to mention that Kan's patch is
upstreamed but not merged to perf/core branch.
v4:
- Updated by Kan's latest patch,
'[PATCH V6 21/25] perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE'
include/uapi/linux/perf_event.h | 15 +++++++++++++++
tools/include/uapi/linux/perf_event.h | 15 +++++++++++++++
2 files changed, 30 insertions(+)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ad15e40d7f5d..14332f4cf816 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -37,6 +37,21 @@ enum perf_type_id {
PERF_TYPE_MAX, /* non-ABI */
};
+/*
+ * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+ * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA
+ * AA: hardware event ID
+ * EEEEEEEE: PMU type ID
+ * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB
+ * BB: hardware cache ID
+ * CC: hardware cache op ID
+ * DD: hardware cache op result ID
+ * EEEEEEEE: PMU type ID
+ * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT 32
+#define PERF_HW_EVENT_MASK 0xffffffff
+
/*
* Generalized performance event event_id types, used by the
* attr.event_id parameter of the sys_perf_event_open()
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index ad15e40d7f5d..14332f4cf816 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -37,6 +37,21 @@ enum perf_type_id {
PERF_TYPE_MAX, /* non-ABI */
};
+/*
+ * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+ * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA
+ * AA: hardware event ID
+ * EEEEEEEE: PMU type ID
+ * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB
+ * BB: hardware cache ID
+ * CC: hardware cache op ID
+ * DD: hardware cache op result ID
+ * EEEEEEEE: PMU type ID
+ * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT 32
+#define PERF_HW_EVENT_MASK 0xffffffff
+
/*
* Generalized performance event event_id types, used by the
* attr.event_id parameter of the sys_perf_event_open()
--
2.17.1