Re: [PATCH v3 01/15] perf/mem: Introduce PERF_MEM_LVLNUM_{EXTN_MEM|IO}

[Ravi Bangoria <ravi.bangoria@amd.com>]

On 30-Sep-22 7:47 PM, Liang, Kan wrote:
> 
> 
> On 2022-09-30 8:50 a.m., Ravi Bangoria wrote:
>> On 30-Sep-22 4:18 PM, kajoljain wrote:
>>>
>>>
>>> On 9/28/22 15:27, Ravi Bangoria wrote:
>>>> PERF_MEM_LVLNUM_EXTN_MEM which can be used to indicate accesses to
>>>> extension memory like CXL etc. PERF_MEM_LVL_IO can be used for IO
>>>> accesses but it can not distinguish between local and remote IO.
>>>> Introduce new field PERF_MEM_LVLNUM_IO which can be clubbed with
>>>> PERF_MEM_REMOTE_REMOTE to indicate Remote IO accesses.
>>>>
>>>> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
>>>> ---
>>>>  include/uapi/linux/perf_event.h | 4 +++-
>>>>  1 file changed, 3 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>>>> index e639c74cf5fb..4ae3c249f675 100644
>>>> --- a/include/uapi/linux/perf_event.h
>>>> +++ b/include/uapi/linux/perf_event.h
>>>> @@ -1336,7 +1336,9 @@ union perf_mem_data_src {
>>>>  #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
>>>>  #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
>>>>  #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
>>>> -/* 5-0xa available */
>>>> +/* 5-0x8 available */
>>>> +#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */
>>>
>>> Hi Ravi,
>>>     Here we are adding entry explicitly for accesses to Extension memory
>>> like CXL. In future if we want to extend it for cache or other accesses
>>> , we again need to add new entries.
>>> Can we rather add single entry say PERF_MEM_LVLNUM_EXTN and further can
>>> use reserved bits to specify memory/cache?
>>
>> Is everybody okay with this:
>>
>> #define PERF_MEM_LVLNUM_EXTN	0x09 /* CXL */
> 
> I think a generic name, PERF_MEM_LVLNUM_EXTN, only make sense, when it
> wants to include all the types of the Extension memory, e.g., CXL, PMEM,
> HBM, etc. Then we can set this bit and the corresponding CXL bits to
> understand the real source. Is it the case here?
> 
> But if it's only for the CXL, I think it's better to use a dedicated
> name, PERF_MEM_LVLNUM_CXL. (as we did for PMEM, PERF_MEM_LVLNUM_PMEM).
> If so, I don't think we need the PERF_MEM_EXTN_CXL_ANY.

Ok. For now, I think below is good enough? Later we can introduce new
variable to provide type of cxl device.


From 5deb2055e2b5b0a61403f2d5f4e5a784b14a65e3 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Sat, 1 Oct 2022 11:37:05 +0530
Subject: [PATCH] perf/mem: Rename PERF_MEM_LVLNUM_EXTN_MEM to
 PERF_MEM_LVLNUM_CXL

PERF_MEM_LVLNUM_EXTN_MEM was introduced to cover CXL devices but it's
bit ambiguous name and also not generic enough to cover cxl.cache and
cxl.io devices. Rename it to PERF_MEM_LVLNUM_CXL to be more specific.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
---
 arch/x86/events/amd/ibs.c       | 2 +-
 include/uapi/linux/perf_event.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3271735f0070..4cb710efbdd9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
 	/* Extension Memory */
 	if (ibs_caps & IBS_CAPS_ZEN4 &&
 	    ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL;
 		if (op_data2->rmt_node) {
 			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
 			/* IBS doesn't provide Remote socket detail */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 85be78e0e7f6..eb1090604d53 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1337,7 +1337,7 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
 /* 5-0x8 available */
-#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */
+#define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
 #define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
-- 
2.31.1