[PATCH 18/22] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters

[kan . liang]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Icelake supports a new CPUID 10.ECX cpu leaf to indicate some fixed
counters are not supported.  This extends the previous count to a bitmap
which allows to disable even lower counters.

It's a nop on Icelake (all fixed counters are supported), but let's
implement it here.  This adds the necessary checks. In theory it could
be used today by a Hypervisor.

For disabled counters disable any constraint events. I reuse the
existing intel_ctrl variable to remember which counters are disabled.
All code that reads all counters is fixed to check this extra bitmask.

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
---
 arch/x86/events/core.c       |  8 +++++++-
 arch/x86/events/intel/core.c | 22 +++++++++++++++-------
 arch/x86/events/perf_event.h |  6 ++++++
 3 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 796e46a59148..283df78c52e0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -225,6 +225,8 @@ static bool check_hw_exists(void)
 		if (ret)
 			goto msr_fail;
 		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+			if (fixed_counter_disabled(i))
+				continue;
 			if (val & (0x03 << i*4)) {
 				bios_fail = 1;
 				val_fail = val;
@@ -1362,6 +1364,8 @@ void perf_event_print_debug(void)
 			cpu, idx, prev_left);
 	}
 	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx))
+			continue;
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -1877,7 +1881,9 @@ static int __init init_hw_perf_events(void)
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
 	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... fixed-purpose events:   %lu\n",
+			hweight64((((1ULL << x86_pmu.num_counters_fixed) - 1)
+					<< INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl));
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3f86af8ce832..433dbd0152a9 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2278,8 +2278,11 @@ static void intel_pmu_reset(void)
 		wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
 		wrmsrl_safe(x86_pmu_event_addr(idx),  0ull);
 	}
-	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx))
+			continue;
 		wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+	}
 
 	if (ds)
 		ds->bts_index = ds->bts_buffer_base;
@@ -4476,7 +4479,7 @@ __init int intel_pmu_init(void)
 	union cpuid10_eax eax;
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
-	unsigned int unused;
+	unsigned int fixed_mask;
 	struct extra_reg *er;
 	int version, i;
 	char *name;
@@ -4497,9 +4500,11 @@ __init int intel_pmu_init(void)
 	 * Check whether the Architectural PerfMon supports
 	 * Branch Misses Retired hw_event or not.
 	 */
-	cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+	cpuid(10, &eax.full, &ebx.full, &fixed_mask, &edx.full);
 	if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
 		return -ENODEV;
+	if (!fixed_mask)
+		fixed_mask = -1;
 
 	version = eax.split.version_id;
 	if (version < 2)
@@ -5017,7 +5022,8 @@ __init int intel_pmu_init(void)
 	}
 
 	x86_pmu.intel_ctrl |=
-		((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+		(((1LL << x86_pmu.num_counters_fixed)-1) & (u64)fixed_mask)
+			<< INTEL_PMC_IDX_FIXED;
 
 	if (x86_pmu.event_constraints) {
 		/*
@@ -5034,9 +5040,11 @@ __init int intel_pmu_init(void)
 				c->weight = hweight64(c->idxmsk64);
 				continue;
 			}
-			if (c->cmask == FIXED_EVENT_FLAGS
-			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			if (c->cmask == FIXED_EVENT_FLAGS)  {
+				if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES)
+					c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+				/* Disabled fixed counters which are not in CPUID */
+				c->idxmsk64 &= x86_pmu.intel_ctrl;
 			}
 			c->idxmsk64 &=
 				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ef8c4d846e87..8894e3bd1f23 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -926,6 +926,12 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
 
+static inline bool fixed_counter_disabled(int i)
+{
+	return x86_pmu.intel_ctrl &&
+		((1ULL << (i + INTEL_PMC_IDX_FIXED)) & x86_pmu.intel_ctrl);
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
-- 
2.17.1