[PATCH v3 2/6] perf mem: Add support for printing PERF_MEM_LVLNUM_L0

From: Dapeng Mi <[email protected]>

Add support for printing PERF_MEM_LVLNUM_L0 in perf mem report.

The L0 cache is newly added a small piece of cache which is
the closest, lowest-latency memory cache tied directly to the
execution pipeline.

The table "Table 9-4. Data Source Field Encodings for Panther
Cove and Coyote Cove Microarchitectures" in the ISE doc chapter
"9.2.1 Panther Cove and Coyote Cove Microarchitectures Memory
Auxiliary Field Layout"[1] indicates the code "01H" means the
"L0 Hit - Minimal latency core cache hit. This request was
satisfied by the L0 data cache."

[1]: https://www.intel.com/content/www/us/en/content-details/922690/intel-architecture-instruction-set-extensions-programming-reference.html

Assisted-by: Sashiko:gemini-3.1-pro-preview
Signed-off-by: Dapeng Mi <[email protected]>
Signed-off-by: Thomas Falcon <[email protected]>
Reviewed-by: Dapeng Mi <[email protected]>
---
v3: Included more information about the L0 cache in the commit message.
---
 tools/perf/Documentation/perf-record.txt | 2 +-
 tools/perf/util/bpf-filter.l             | 1 +
 tools/perf/util/mem-events.c             | 5 +++++
 tools/perf/util/mem-events.h             | 1 +
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 178f483140ed..b54032efe41c 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -212,7 +212,7 @@ OPTIONS
 	The <value> can be one of:
 	  <number> (for any term)
 	  na, load, store, pfetch, exec (for mem_op)
-	  l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
+	  l0, l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
 	  na, none, hit, miss, hitm, fwd, peer (for mem_snoop)
 	  remote (for mem_remote)
 	  na, locked (for mem_locked)
diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l
index 6aa65ade3385..1be9df6550fc 100644
--- a/tools/perf/util/bpf-filter.l
+++ b/tools/perf/util/bpf-filter.l
@@ -131,6 +131,7 @@ store		{ return constant(PERF_MEM_OP_STORE); }
 pfetch		{ return constant(PERF_MEM_OP_PFETCH); }
 exec		{ return constant(PERF_MEM_OP_EXEC); }
 
+l0		{ return constant(PERF_MEM_LVLNUM_L0); }
 l1		{ return constant(PERF_MEM_LVLNUM_L1); }
 l2		{ return constant(PERF_MEM_LVLNUM_L2); }
 l3		{ return constant(PERF_MEM_LVLNUM_L3); }
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 4e490f9cd348..4fd48fd20055 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -391,6 +391,7 @@ static const char * const mem_lvlnum[] = {
 	[PERF_MEM_LVLNUM_L4] = "L4",
 	[PERF_MEM_LVLNUM_L2_MHB] = "L2 MHB",
 	[PERF_MEM_LVLNUM_MSC] = "Memory-side Cache",
+	[PERF_MEM_LVLNUM_L0] = "L0",
 	[PERF_MEM_LVLNUM_UNC] = "Uncached",
 	[PERF_MEM_LVLNUM_CXL] = "CXL",
 	[PERF_MEM_LVLNUM_IO] = "I/O",
@@ -831,6 +832,8 @@ int mem_stat_index(const enum mem_stat_type mst, const u64 val)
 		}
 	case PERF_MEM_STAT_CACHE:
 		switch (src.mem_lvl_num) {
+		case PERF_MEM_LVLNUM_L0:
+			return MEM_STAT_CACHE_L0;
 		case PERF_MEM_LVLNUM_L1:
 			return MEM_STAT_CACHE_L1;
 		case PERF_MEM_LVLNUM_L2:
@@ -915,6 +918,8 @@ const char *mem_stat_name(const enum mem_stat_type mst, const int idx)
 		}
 	case PERF_MEM_STAT_CACHE:
 		switch (idx) {
+		case MEM_STAT_CACHE_L0:
+			return "L0";
 		case MEM_STAT_CACHE_L1:
 			return "L1";
 		case MEM_STAT_CACHE_L2:
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 5b98076904b0..daa22748f9fe 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -109,6 +109,7 @@ enum mem_stat_op {
 };
 
 enum mem_stat_cache {
+	MEM_STAT_CACHE_L0,
 	MEM_STAT_CACHE_L1,
 	MEM_STAT_CACHE_L2,
 	MEM_STAT_CACHE_L3,
-- 
2.55.0