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.

For ex: Encodings for mem_hops fields with L2 cache:

L2			- local L2
L2 | REMOTE | HOPS_0	- remote core, same node L2

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211006140654.298352-3-kjain@linux.ibm.com

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index a74538c..bd8860e 100644 (file)
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1225,14 +1225,16 @@ 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 */
@@ -1328,6 +1330,11 @@ 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)