[Patch v9 10/24] perf/x86/intel: Consolidate PMU capability updates

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

Currently, the PERF_PMU_CAP_EXTENDED_REGS capability is set in two
different places: intel_ds_pebs_init() and __intel_update_pmu_caps()
for adaptive and architectural PEBS. The upcoming XSAVES-based SIMD
register sampling will also require setting and validating this
capability. Managing it across multiple locations introduces
unnecessary complexity and potential conflicts.

To centralize and simplify the PERF_PMU_CAP_EXTENDED_REGS logic,
consolidate its initialization into a single helper function,
__intel_update_pmu_xregs_caps(), handling both adaptive and
architectural PEBS.

Additionally, optimize the capability update paths by moving the
initialization of intel_cap.capabilities out of the update_pmu_cap()
helper. The helper is guarded by archPerfmonExt support, whereas
intel_cap.capabilities is independent of it.

Finally, introduce a new wrapper function, intel_update_pmu_caps(),
to cleanly encapsulate all these PMU capability updates.

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/intel/core.c | 54 ++++++++++++++++++++++++------------
 arch/x86/events/intel/ds.c   |  1 -
 2 files changed, 36 insertions(+), 19 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2e658b4bc83a..11a0c4dd2026 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6143,19 +6143,27 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
 
 static inline bool intel_pmu_broken_perf_cap(void)
 {
-	/* The Perf Metric (Bit 15) is always cleared */
-	if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
+	/*
+	 * The Perf Metric (Bit 15) is always cleared on P-core of
+	 * PRL and MTL. Details can be found in RPL018 Errata Details.
+	 */
+	if (boot_cpu_data.x86_vfm == INTEL_RAPTORLAKE ||
+	    boot_cpu_data.x86_vfm == INTEL_RAPTORLAKE_P ||
+	    boot_cpu_data.x86_vfm == INTEL_RAPTORLAKE_S ||
+	    boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
 	    boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L)
 		return true;
 
 	return false;
 }
 
-static inline void __intel_update_pmu_caps(struct pmu *pmu)
+static inline void __intel_update_pmu_xregs_caps(struct pmu *pmu)
 {
 	struct pmu *dest_pmu = pmu ? pmu : x86_get_pmu(smp_processor_id());
+	u64 caps = hybrid(pmu, arch_pebs_cap).caps;
 
-	if (hybrid(pmu, arch_pebs_cap).caps & ARCH_PEBS_VECR_XMM)
+	if ((x86_pmu.arch_pebs && (caps & ARCH_PEBS_VECR_XMM)) ||
+	    (x86_pmu.intel_cap.pebs_format >= 4 && x86_pmu.intel_cap.pebs_baseline))
 		dest_pmu->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 }
 
@@ -6179,7 +6187,7 @@ static inline void __intel_update_large_pebs_flags(struct pmu *pmu)
 
 #define counter_mask(_gp, _fixed) ((_gp) | ((u64)(_fixed) << INTEL_PMC_IDX_FIXED))
 
-static void update_pmu_cap(struct pmu *pmu)
+static void update_pmu_cap_from_perfmonext(struct pmu *pmu)
 {
 	unsigned int eax, ebx, ecx, edx;
 	union cpuid35_eax eax_0;
@@ -6227,21 +6235,34 @@ static void update_pmu_cap(struct pmu *pmu)
 		hybrid(pmu, arch_pebs_cap).counters = pebs_mask;
 		hybrid(pmu, arch_pebs_cap).pdists = pdists_mask;
 
-		if (WARN_ON((pebs_mask | pdists_mask) & ~cntrs_mask)) {
+		if (WARN_ON((pebs_mask | pdists_mask) & ~cntrs_mask))
 			x86_pmu.arch_pebs = 0;
-		} else {
-			__intel_update_pmu_caps(pmu);
+		else
 			__intel_update_large_pebs_flags(pmu);
-		}
 	} else {
 		WARN_ON(x86_pmu.arch_pebs == 1);
 		x86_pmu.arch_pebs = 0;
 	}
+}
 
-	if (!intel_pmu_broken_perf_cap()) {
-		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
-		rdmsrq(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
+static void intel_update_pmu_caps(struct pmu *pmu)
+{
+	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		update_pmu_cap_from_perfmonext(pmu);
+
+	if (is_hybrid() && this_cpu_has(X86_FEATURE_PDCM)) {
+		rdmsrq(MSR_IA32_PERF_CAPABILITIES,
+		       hybrid(pmu, intel_cap).capabilities);
+
+		/*
+		 * Restore perf_metrics on platforms with broken
+		 * perf_capablities.
+		 */
+		if (intel_pmu_broken_perf_cap() &&
+		    hybrid_pmu(pmu)->pmu_type == hybrid_big)
+			hybrid(pmu, intel_cap).perf_metrics = 1;
 	}
+	__intel_update_pmu_xregs_caps(pmu);
 }
 
 static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
@@ -6325,8 +6346,7 @@ static bool init_hybrid_pmu(int cpu)
 	if (!cpumask_empty(&pmu->supported_cpus))
 		goto end;
 
-	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
-		update_pmu_cap(&pmu->pmu);
+	intel_update_pmu_caps(&pmu->pmu);
 
 	intel_pmu_check_hybrid_pmus(pmu);
 
@@ -6395,8 +6415,6 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 	}
 
-	__intel_update_pmu_caps(cpuc->pmu);
-
 	if (!cpuc->shared_regs)
 		return;
 
@@ -8821,8 +8839,8 @@ __init int intel_pmu_init(void)
 	 * from the leaf 0xa. The core specific update will be done later
 	 * when a new type is online.
 	 */
-	if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
-		update_pmu_cap(NULL);
+	if (!is_hybrid())
+		intel_update_pmu_caps(NULL);
 
 	if (x86_pmu.arch_pebs) {
 		static_call_update(intel_pmu_disable_event_ext,
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7b69f8c8d0c2..78b9c0dcb14d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -3396,7 +3396,6 @@ static void __init intel_ds_pebs_init(void)
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
 				x86_pmu.pebs_capable = ~0ULL;
 				pebs_qual = "-baseline";
-				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
 				/* Only basic record supported */
 				x86_pmu.large_pebs_flags &=
-- 
2.34.1