arch/x86/events/intel/core.c | 137 ++++++++++++++++++++++++++++++++-- arch/x86/events/intel/ds.c | 2 +- 2 files changed, 131 insertions(+), 8 deletions(-)
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 4ef863352bcde482d65722ed721c3fd3967a67d6
Gitweb: https://git.kernel.org/tip/4ef863352bcde482d65722ed721c3fd3967a67d6
Author: Dapeng Mi <dapeng1.mi@linux.intel.com>
AuthorDate: Fri, 15 May 2026 14:11:36 +08:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 19 May 2026 13:49:03 +02:00
perf/x86/intel: Update event constraints and cache_extra_regsfor ADL
Update perf hard-coded event constraints and cache_extra_regs[] for
Alderlake according to the latest ADL perfmon events (V1.39).
One important note is that ADL has differences on the L3/node related
OCR events although it shares same uarch with SPR server, e.g.,
ADL has different extra MSR values and no node events. So some variants
of structures and functions are introduced to reflect these
differences, like adl_glc_hw_cache_event_ids[],
adl_glc_hw_cache_extra_regs[] and intel_pmu_init_glc_hybrid(), etc.
Please note these changes would temporarily impact other platforms like
MTL/ARL-U which shares hard-coded event structures, but it would be
fixed soon in subsequent patches.
ADL perfmon events:
https://github.com/intel/perfmon/blob/main/ADL/events/alderlake_goldencove_core.json
https://github.com/intel/perfmon/blob/main/ADL/events/alderlake_gracemont_core.json
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260515061143.338553-5-dapeng1.mi@linux.intel.com
---
arch/x86/events/intel/core.c | 137 ++++++++++++++++++++++++++++++++--
arch/x86/events/intel/ds.c | 2 +-
2 files changed, 131 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index da2ade0..be86051 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -215,8 +215,10 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
static struct event_constraint intel_grt_event_constraints[] __read_mostly = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* pseudo INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0200, 1), /* pseudo CPU_CLK_UNHALTED.THREAD */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF_TSC */
FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
EVENT_CONSTRAINT_END
};
@@ -713,6 +715,80 @@ static __initconst const u64 glc_hw_cache_event_ids
},
};
+/* ADL P-core (Golden cove) specific event code. */
+static __initconst const u64 adl_glc_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x81d0,
+ [ C(RESULT_MISS) ] = 0xe124,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x82d0,
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_MISS) ] = 0xe424,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x12a,
+ [ C(RESULT_MISS) ] = 0x12a,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x12a,
+ [ C(RESULT_MISS) ] = 0x12a,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x81d0,
+ [ C(RESULT_MISS) ] = 0xe12,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x82d0,
+ [ C(RESULT_MISS) ] = 0xe13,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = 0xe11,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4c4,
+ [ C(RESULT_MISS) ] = 0x4c5,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static __initconst const u64 glc_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -736,6 +812,24 @@ static __initconst const u64 glc_hw_cache_extra_regs
},
};
+/* ADL P-core (Golden cove) specific extra regs value. */
+static __initconst const u64 adl_glc_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) ] = 0x3fbfc00001, /* OCR.DEMAND_DATA_RD.L3_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x10002, /* OCR.DEMAND_RFO.ANY_RESPONSE */
+ [ C(RESULT_MISS) ] = 0x3fbfc00002, /* OCR.DEMAND_RFO.L3_MISS */
+ },
+ },
+};
+
static __initconst const u64 pnc_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2384,6 +2478,23 @@ static __initconst const u64 tnt_hw_cache_extra_regs
},
};
+static __initconst const u64 grt_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)] = 0x3F84400001, /* OCR.DEMAND_DATA_RD.L3_MISS */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0x10002, /* OCR.DEMAND_RFO.ANY_RESPONSE */
+ [C(RESULT_MISS)] = 0x3F84400002, /* 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]
@@ -2434,9 +2545,12 @@ static struct attribute *grt_mem_attrs[] = {
};
static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
- /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
- INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
- INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+ /*
+ * Must define OFFCORE_RSP_X first, see intel_fixup_er().
+ * Bit 63 only valid on OFFCORE_RSP_0 MSR.
+ */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x8003f03fffffffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x3f03fffffffffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x5d0),
EVENT_EXTRA_END
};
@@ -7533,6 +7647,15 @@ static __always_inline void intel_pmu_init_glc(struct pmu *pmu)
intel_pmu_ref_cycles_ext();
}
+static __always_inline void intel_pmu_init_glc_hybrid(struct pmu *pmu)
+{
+ intel_pmu_init_glc(pmu);
+
+ /* ADL has different extra MSR values from Server for the L3 or node OCR/OMR events. */
+ memcpy(hybrid_var(pmu, hw_cache_event_ids), adl_glc_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hybrid_var(pmu, hw_cache_extra_regs), adl_glc_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+}
+
static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
{
x86_pmu.mid_ack = true;
@@ -7545,7 +7668,7 @@ static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
memcpy(hybrid_var(pmu, hw_cache_event_ids), glp_hw_cache_event_ids, sizeof(hw_cache_event_ids));
- memcpy(hybrid_var(pmu, hw_cache_extra_regs), tnt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ memcpy(hybrid_var(pmu, hw_cache_extra_regs), grt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
hybrid_var(pmu, hw_cache_event_ids)[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
hybrid(pmu, event_constraints) = intel_grt_event_constraints;
hybrid(pmu, pebs_constraints) = intel_grt_pebs_event_constraints;
@@ -8304,7 +8427,7 @@ __init int intel_pmu_init(void)
/* Initialize big core specific PerfMon capabilities.*/
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
- intel_pmu_init_glc(&pmu->pmu);
+ intel_pmu_init_glc_hybrid(&pmu->pmu);
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
pmu->cntr_mask64 <<= 2;
pmu->cntr_mask64 |= 0x3;
@@ -8361,7 +8484,7 @@ __init int intel_pmu_init(void)
/* Initialize big core specific PerfMon capabilities.*/
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
- intel_pmu_init_glc(&pmu->pmu);
+ intel_pmu_init_glc_hybrid(&pmu->pmu);
pmu->extra_regs = intel_rwc_extra_regs;
/* Initialize Atom core specific PerfMon capabilities.*/
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7f0d515..efab3cb 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1292,7 +1292,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
struct event_constraint intel_grt_pebs_event_constraints[] = {
/* Allow all events as PEBS with no flags */
INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
- INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
+ INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0x3f),
EVENT_CONSTRAINT_END
};
© 2016 - 2026 Red Hat, Inc.