From f4c6217f7f5936f7173d028559ff5d25cce10816 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:51 +0530 Subject: perf: Add comment about current state of PERF_MEM_LVL_* namespace and remove an extra line Add a comment about PERF_MEM_LVL_* namespace being depricated to some extent in favour of added PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. Remove an extra line present in perf_mem__lvl_scnprintf function. Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-2-kjain@linux.ibm.com --- tools/include/uapi/linux/perf_event.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..e1701e9c7858 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1241,7 +1241,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ -- cgit From cae1d759065ee989de246d4a72bc2bfe9ad9d262 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:53 +0530 Subject: tools/perf: Add mem_hops field in perf_mem_data_src structure Going forward, future generation systems can have more hierarchy within the node/package level but currently we don't have any data source encoding field in perf, which can be used to represent this level of data. Add a new field called 'mem_hops' in the perf_mem_data_src structure which can be used to represent intra-node/package or inter-node/off-package details. This field is of size 3 bits where PERF_MEM_HOPS_{NA, 0..6} value can be used to present different hop levels data. Also add corresponding macros to define mem_hop field values and shift value. Currently we define macro for HOPS_0 which corresponds to data coming from another core but same node. Add functionality to represent mem_hop field data in perf_mem__lvl_scnprintf function with the help of added string array called mem_hops. For ex: Encodings for mem_hops fields with L2 cache: L2 - local L2 L2 | REMOTE | HOPS_0 - remote core, same node L2 Since with the addition of HOPS field, now remote can be used to denote cache access from the same node but different core, a check is added in the c2c_decode_stats function to set mrem only when HOPS is zero along with set remote field. Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-4-kjain@linux.ibm.com --- tools/include/uapi/linux/perf_event.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index e1701e9c7858..2fc09579e24a 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1210,14 +1210,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1313,6 +1315,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit