perf/x86/intel: Setup PEBS data configuration and enable legacy groups

Different with legacy PEBS, arch-PEBS provides per-counter PEBS data
configuration by programing MSR IA32_PMC_GPx/FXx_CFG_C MSRs.

This patch obtains PEBS data configuration from event attribute and then
writes the PEBS data configuration to MSR IA32_PMC_GPx/FXx_CFG_C and
enable corresponding PEBS groups.

Please notice this patch only enables XMM SIMD regs sampling for
arch-PEBS, the other SIMD regs (OPMASK/YMM/ZMM) sampling on arch-PEBS
would be supported after PMI based SIMD regs (OPMASK/YMM/ZMM) sampling
is supported.

Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251029102136.61364-12-dapeng1.mi@linux.intel.com

Author: Dapeng Mi

arch/x86/events/intel/core.c

@@ -2563,6 +2563,45 @@ static void intel_pmu_disable_fixed(struct perf_event *event)
 	cpuc->fixed_ctrl_val &= ~mask;
 }
 
+static inline void __intel_pmu_update_event_ext(int idx, u64 ext)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u32 msr;
+
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		msr = MSR_IA32_PMC_V6_GP0_CFG_C +
+		      x86_pmu.addr_offset(idx, false);
+	} else {
+		msr = MSR_IA32_PMC_V6_FX0_CFG_C +
+		      x86_pmu.addr_offset(idx - INTEL_PMC_IDX_FIXED, false);
+	}
+
+	cpuc->cfg_c_val[idx] = ext;
+	wrmsrq(msr, ext);
+}
+
+static void intel_pmu_disable_event_ext(struct perf_event *event)
+{
+	if (!x86_pmu.arch_pebs)
+		return;
+
+	/*
+	 * Only clear CFG_C MSR for PEBS counter group events,
+	 * it avoids the HW counter's value to be added into
+	 * other PEBS records incorrectly after PEBS counter
+	 * group events are disabled.
+	 *
+	 * For other events, it's unnecessary to clear CFG_C MSRs
+	 * since CFG_C doesn't take effect if counter is in
+	 * disabled state. That helps to reduce the WRMSR overhead
+	 * in context switches.
+	 */
+	if (!is_pebs_counter_event_group(event))
+		return;
+
+	__intel_pmu_update_event_ext(event->hw.idx, 0);
+}
+
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -2571,9 +2610,12 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		intel_clear_masks(event, idx);
+		intel_pmu_disable_event_ext(event);
 		x86_pmu_disable_event(event);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+		intel_pmu_disable_event_ext(event);
+		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_disable_fixed(event);
 		break;
@@ -2940,6 +2982,66 @@ static void intel_pmu_enable_acr(struct perf_event *event)
 
 DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 
+static void intel_pmu_enable_event_ext(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	union arch_pebs_index old, new;
+	struct arch_pebs_cap cap;
+	u64 ext = 0;
+
+	if (!x86_pmu.arch_pebs)
+		return;
+
+	cap = hybrid(cpuc->pmu, arch_pebs_cap);
+
+	if (event->attr.precise_ip) {
+		u64 pebs_data_cfg = intel_get_arch_pebs_data_config(event);
+
+		ext |= ARCH_PEBS_EN;
+		if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD)
+			ext |= (-hwc->sample_period) & ARCH_PEBS_RELOAD;
+
+		if (pebs_data_cfg && cap.caps) {
+			if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+				ext |= ARCH_PEBS_AUX & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_GP)
+				ext |= ARCH_PEBS_GPR & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+				ext |= ARCH_PEBS_VECR_XMM & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+				ext |= ARCH_PEBS_LBR & cap.caps;
+		}
+
+		if (cpuc->n_pebs == cpuc->n_large_pebs)
+			new.thresh = ARCH_PEBS_THRESH_MULTI;
+		else
+			new.thresh = ARCH_PEBS_THRESH_SINGLE;
+
+		rdmsrq(MSR_IA32_PEBS_INDEX, old.whole);
+		if (new.thresh != old.thresh || !old.en) {
+			if (old.thresh == ARCH_PEBS_THRESH_MULTI && old.wr > 0) {
+				/*
+				 * Large PEBS was enabled.
+				 * Drain PEBS buffer before applying the single PEBS.
+				 */
+				intel_pmu_drain_pebs_buffer();
+			} else {
+				new.wr = 0;
+				new.full = 0;
+				new.en = 1;
+				wrmsrq(MSR_IA32_PEBS_INDEX, new.whole);
+			}
+		}
+	}
+
+	if (cpuc->cfg_c_val[hwc->idx] != ext)
+		__intel_pmu_update_event_ext(hwc->idx, ext);
+}
+
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2955,10 +3057,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
 		static_call_cond(intel_pmu_enable_acr_event)(event);
+		intel_pmu_enable_event_ext(event);
 		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
 		static_call_cond(intel_pmu_enable_acr_event)(event);
+		intel_pmu_enable_event_ext(event);
 		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
@@ -5301,6 +5405,30 @@ static inline bool intel_pmu_broken_perf_cap(void)
 	return false;
 }
 
+static inline void __intel_update_pmu_caps(struct pmu *pmu)
+{
+	struct pmu *dest_pmu = pmu ? pmu : x86_get_pmu(smp_processor_id());
+
+	if (hybrid(pmu, arch_pebs_cap).caps & ARCH_PEBS_VECR_XMM)
+		dest_pmu->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
+}
+
+static inline void __intel_update_large_pebs_flags(struct pmu *pmu)
+{
+	u64 caps = hybrid(pmu, arch_pebs_cap).caps;
+
+	x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
+	if (caps & ARCH_PEBS_LBR)
+		x86_pmu.large_pebs_flags |= PERF_SAMPLE_BRANCH_STACK;
+
+	if (!(caps & ARCH_PEBS_AUX))
+		x86_pmu.large_pebs_flags &= ~PERF_SAMPLE_DATA_SRC;
+	if (!(caps & ARCH_PEBS_GPR)) {
+		x86_pmu.large_pebs_flags &=
+			~(PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER);
+	}
+}
+
 #define counter_mask(_gp, _fixed) ((_gp) | ((u64)(_fixed) << INTEL_PMC_IDX_FIXED))
 
 static void update_pmu_cap(struct pmu *pmu)
@@ -5349,8 +5477,12 @@ 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);
+			__intel_update_large_pebs_flags(pmu);
+		}
 	} else {
 		WARN_ON(x86_pmu.arch_pebs == 1);
 		x86_pmu.arch_pebs = 0;
@@ -5514,6 +5646,8 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 	}
 
+	__intel_update_pmu_caps(cpuc->pmu);
+
 	if (!cpuc->shared_regs)
 		return;
 

arch/x86/events/intel/ds.c

@@ -1528,6 +1528,18 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 	}
 }
 
+u64 intel_get_arch_pebs_data_config(struct perf_event *event)
+{
+	u64 pebs_data_cfg = 0;
+
+	if (WARN_ON(event->hw.idx < 0 || event->hw.idx >= X86_PMC_IDX_MAX))
+		return 0;
+
+	pebs_data_cfg |= pebs_update_adaptive_cfg(event);
+
+	return pebs_data_cfg;
+}
+
 void intel_pmu_pebs_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -2947,6 +2959,11 @@ static void intel_pmu_drain_arch_pebs(struct pt_regs *iregs,
 
 	index.wr = 0;
 	index.full = 0;
+	index.en = 1;
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
+		index.thresh = ARCH_PEBS_THRESH_MULTI;
+	else
+		index.thresh = ARCH_PEBS_THRESH_SINGLE;
 	wrmsrq(MSR_IA32_PEBS_INDEX, index.whole);
 
 	mask = hybrid(cpuc->pmu, arch_pebs_cap).counters & cpuc->pebs_enabled;

arch/x86/events/perf_event.h

@@ -304,6 +304,8 @@ struct cpu_hw_events {
 	/* Intel ACR configuration */
 	u64			acr_cfg_b[X86_PMC_IDX_MAX];
 	u64			acr_cfg_c[X86_PMC_IDX_MAX];
+	/* Cached CFG_C values */
+	u64			cfg_c_val[X86_PMC_IDX_MAX];
 
 	/*
 	 * Intel LBR bits
@@ -1782,6 +1784,8 @@ void intel_pmu_pebs_data_source_cmt(void);
 
 void intel_pmu_pebs_data_source_lnl(void);
 
+u64 intel_get_arch_pebs_data_config(struct perf_event *event);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);

arch/x86/include/asm/intel_ds.h

@@ -7,6 +7,13 @@
 #define PEBS_BUFFER_SHIFT	4
 #define PEBS_BUFFER_SIZE	(PAGE_SIZE << PEBS_BUFFER_SHIFT)
 
+/*
+ * The largest PEBS record could consume a page, ensure
+ * a record at least can be written after triggering PMI.
+ */
+#define ARCH_PEBS_THRESH_MULTI	((PEBS_BUFFER_SIZE - PAGE_SIZE) >> PEBS_BUFFER_SHIFT)
+#define ARCH_PEBS_THRESH_SINGLE	1
+
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS_FMT4	8
 #define MAX_PEBS_EVENTS		32

arch/x86/include/asm/msr-index.h

@@ -333,6 +333,14 @@
 #define ARCH_PEBS_OFFSET_MASK		0x7fffff
 #define ARCH_PEBS_INDEX_WR_SHIFT	4
 
+#define ARCH_PEBS_RELOAD		0xffffffff
+#define ARCH_PEBS_LBR_SHIFT		40
+#define ARCH_PEBS_LBR			(0x3ull << ARCH_PEBS_LBR_SHIFT)
+#define ARCH_PEBS_VECR_XMM		BIT_ULL(49)
+#define ARCH_PEBS_GPR			BIT_ULL(61)
+#define ARCH_PEBS_AUX			BIT_ULL(62)
+#define ARCH_PEBS_EN			BIT_ULL(63)
+
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
 #define RTIT_CTL_CYCLEACC		BIT(1)