perf/x86: Support counter mask

The current perf assumes that both GP and fixed counters are contiguous.
But it's not guaranteed on newer Intel platforms or in a virtualization
environment.

Use the counter mask to replace the number of counters for both GP and
the fixed counters. For the other ARCHs or old platforms which don't
support a counter mask, using GENMASK_ULL(num_counter - 1, 0) to
replace. There is no functional change for them.

The interface to KVM is not changed. The number of counters still be
passed to KVM. It can be updated later separately.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lkml.kernel.org/r/20240626143545.480761-3-kan.liang@linux.intel.com

arch/x86/events/amd/core.c

@@ -432,7 +432,7 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *tmp = event;
 
 		if (try_cmpxchg(nb->owners + i, &tmp, NULL))
@@ -501,7 +501,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+	for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
 		if (new == -1 || hwc->idx == idx)
 			/* assign free slot, prefer hwc->idx */
 			old = cmpxchg(nb->owners + idx, NULL, event);
@@ -544,7 +544,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -737,7 +737,7 @@ static void amd_pmu_check_overflow(void)
 	 * counters are always enabled when this function is called and
 	 * ARCH_PERFMON_EVENTSEL_INT is always set.
 	 */
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -757,7 +757,7 @@ static void amd_pmu_enable_all(int added)
 
 	amd_brs_enable_all();
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		/* only activate events which are marked as active */
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -980,7 +980,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	/* Clear any reserved bits set by buggy microcode */
 	status &= amd_pmu_global_cntr_mask;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1315,7 +1315,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.addr_offset            = amd_pmu_addr_offset,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_counters		= AMD64_NUM_COUNTERS,
+	.cntr_mask64		= GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
 	.add			= amd_pmu_add_event,
 	.del			= amd_pmu_del_event,
 	.cntval_bits		= 48,
@@ -1414,7 +1414,7 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
-	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+	x86_pmu.cntr_mask64	= GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
 
 	/* Check for Performance Monitoring v2 support */
 	if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1424,9 +1424,9 @@ static int __init amd_core_pmu_init(void)
 		x86_pmu.version = 2;
 
 		/* Find the number of available Core PMCs */
-		x86_pmu.num_counters = ebx.split.num_core_pmc;
+		x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
 
-		amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+		amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
 
 		/* Update PMC handling functions */
 		x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1454,12 +1454,12 @@ static int __init amd_core_pmu_init(void)
 		 * even numbered counter that has a consecutive adjacent odd
 		 * numbered counter following it.
 		 */
-		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+		for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
 			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
-				    x86_pmu.num_counters / 2, 0,
+				    x86_pmu_max_num_counters(NULL) / 2, 0,
 				    PERF_X86_EVENT_PAIR);
 
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;

arch/x86/events/intel/ds.c

@@ -1138,7 +1138,6 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	u64 threshold;
 	int reserved;
 
@@ -1146,7 +1145,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 		return;
 
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-		reserved = max_pebs_events + num_counters_fixed;
+		reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
 	else
 		reserved = max_pebs_events;
 
@@ -2172,8 +2171,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	mask = x86_pmu.pebs_events_mask;
 	size = max_pebs_events;
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
-		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
-		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+		mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
 	}
 
 	if (unlikely(base >= top)) {
@@ -2269,11 +2268,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	int bit, size;
+	int bit;
 	u64 mask;
 
 	if (!x86_pmu.pebs_active)
@@ -2285,11 +2283,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	ds->pebs_index = ds->pebs_buffer_base;
 
 	mask = hybrid(cpuc->pmu, pebs_events_mask) |
-	       (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
-	size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
+	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
 		return;
 	}
 
@@ -2299,11 +2296,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
 		pebs_status &= mask;
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
 			counts[bit]++;
 	}
 
-	for_each_set_bit(bit, (unsigned long *)&mask, size) {
+	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
 		if (counts[bit] == 0)
 			continue;
 

arch/x86/events/intel/knc.c

@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
 	.apic			= 1,
 	.max_period		= (1ULL << 39) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	.cntval_bits		= 40,
 	.cntval_mask		= (1ULL << 40) - 1,
 	.get_event_constraints	= x86_get_event_constraints,

arch/x86/events/intel/p4.c

@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		int overflow;
 
 		if (!test_bit(idx, cpuc->active_mask)) {
@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * though leave it restricted at moment assuming
 	 * HT is on
 	 */
-	.num_counters		= ARCH_P4_MAX_CCCR,
+	.cntr_mask64		= GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
 	.apic			= 1,
 	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
 	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
 	 *
 	 * Solve this by zero'ing out the registers to mimic a reset.
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
 		wrmsrl_safe(reg, 0ULL);
 	}

arch/x86/events/intel/p6.c

@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the

arch/x86/events/perf_event.h

@@ -685,8 +685,14 @@ struct x86_hybrid_pmu {
 	union perf_capabilities		intel_cap;
 	u64				intel_ctrl;
 	u64				pebs_events_mask;
-	int				num_counters;
-	int				num_counters_fixed;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -774,8 +780,14 @@ struct x86_pmu {
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
-	int		num_counters;
-	int		num_counters_fixed;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -1125,8 +1137,8 @@ static inline int x86_pmu_rdpmc_index(int index)
 	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
-bool check_hw_exists(struct pmu *pmu, int num_counters,
-		     int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask);
 
 int x86_add_exclusive(unsigned int what);
 
@@ -1197,8 +1209,27 @@ void x86_pmu_enable_event(struct perf_event *event);
 
 int x86_pmu_handle_irq(struct pt_regs *regs);
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
 
 extern struct event_constraint emptyconstraint;
 

arch/x86/events/zhaoxin/core.c

@@ -530,13 +530,13 @@ __init int zhaoxin_pmu_init(void)
 	pr_info("Version check pass!\n");
 
 	x86_pmu.version			= version;
-	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntr_mask64		= GENMASK_ULL(eax.split.num_counters - 1, 0);
 	x86_pmu.cntval_bits		= eax.split.bit_width;
 	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 	x86_pmu.events_maskl		= ebx.full;
 	x86_pmu.events_mask_len		= eax.split.mask_length;
 
-	x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+	x86_pmu.fixed_cntr_mask64	= GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
 	x86_add_quirk(zhaoxin_arch_events_quirk);
 
 	switch (boot_cpu_data.x86) {
@@ -604,13 +604,13 @@ __init int zhaoxin_pmu_init(void)
 		return -ENODEV;
 	}
 
-	x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
-	x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+	x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 |= x86_pmu.cntr_mask64;
+			c->weight += x86_pmu_num_counters(NULL);
 		}
 	}