[PATCH 11/11] perf/x86/intel: Update event constraints and cache_extra_regs[] for CWF

[Dapeng Mi <dapeng1.mi@linux.intel.com>]

Update perf hard-coded event constraints and cache_extra_regs[] for
Clearwater Forest according to the latest CWF perfmon events (V1.02).

An important difference is that CWF introduce new extra register values
for the L3 cache OCR events, so define darkmont specific
dkt_hw_cache_extra_regs[] array.

CWF perfmon events:
https://github.com/intel/perfmon/blob/main/CWF/events/clearwaterforest_core.json

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/intel/core.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e1c6fb127f10..eaa25239f2ec 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2582,6 +2582,22 @@ static __initconst const u64 skt_hw_cache_extra_regs
 	},
 };
 
+static __initconst const u64 dkt_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x10001,		/* OCR.DEMAND_DATA_RD.ANY_RESPONSE */
+			[C(RESULT_MISS)]	= 0x33FBFC00001,	/* OCR.DEMAND_DATA_RD.L3_MISS */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x10002,		/* OCR.DEMAND_RFO.ANY_RESPONSE */
+			[C(RESULT_MISS)]	= 0x33FBFC00002,	/* OCR.DEMAND_RFO.L3_MISS */
+		},
+	},
+};
+
 static __initconst const u64 arw_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -7779,6 +7795,18 @@ static __always_inline void intel_pmu_init_dkt_hybrid(struct pmu *pmu)
 	hybrid(pmu, pebs_constraints) = intel_dkt_pebs_event_constraints;
 }
 
+/*
+ * Darkmont is used by the CWF and PTL E-cores, but their L3 OCR
+ * events require different extra MSR values. Keep a separate init
+ * function for the non-hybrid server variant.
+ */
+static __always_inline void intel_pmu_init_dkt(struct pmu *pmu)
+{
+	intel_pmu_init_dkt_hybrid(pmu);
+	memcpy(hybrid_var(pmu, hw_cache_extra_regs),
+	       dkt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+}
+
 static __always_inline void intel_pmu_init_arw(struct pmu *pmu)
 {
 	intel_pmu_init_grt(pmu);
@@ -8113,7 +8141,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_ATOM_DARKMONT_X:
-		intel_pmu_init_skt(NULL);
+		intel_pmu_init_dkt(NULL);
 		intel_pmu_pebs_data_source_cmt();
 		x86_pmu.pebs_latency_data = cmt_latency_data;
 		x86_pmu.get_event_constraints = cmt_get_event_constraints;
-- 
2.34.1