Merge branch kvm-arm64/6.6/pmu-fixes into kvmarm-master/next

* kvm-arm64/6.6/pmu-fixes:
  : .
  : Another set of PMU fixes, coutrtesy of Reiji Watanabe.
  : From the cover letter:
  :
  : "This series fixes a couple of PMUver related handling of
  : vPMU support.
  :
  : On systems where the PMUVer is not uniform across all PEs,
  : KVM currently does not advertise PMUv3 to the guest,
  : even if userspace successfully runs KVM_ARM_VCPU_INIT with
  : KVM_ARM_VCPU_PMU_V3."
  :
  : Additionally, a fix for an obscure counter oversubscription
  : issue happening when the hsot profines the guest's EL0.
  : .
  KVM: arm64: pmu: Guard PMU emulation definitions with CONFIG_KVM
  KVM: arm64: pmu: Resync EL0 state on counter rotation
  KVM: arm64: PMU: Don't advertise STALL_SLOT_{FRONTEND,BACKEND}
  KVM: arm64: PMU: Don't advertise the STALL_SLOT event
  KVM: arm64: PMU: Avoid inappropriate use of host's PMUVer
  KVM: arm64: PMU: Disallow vPMU on non-uniform PMUVer

Signed-off-by: Marc Zyngier <maz@kernel.org>

7 files changed, 55 insertions, 12 deletions

diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
index f3cd04ff022d..72529f5e2bed 100644
--- a/arch/arm/include/asm/arm_pmuv3.h
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -227,6 +227,8 @@ static inline bool kvm_set_pmuserenr(u64 val)
 	return false;
 }
 
+static inline void kvm_vcpu_pmu_resync_el0(void) {}
+
 /* PMU Version in DFR Register */
 #define ARMV8_PMU_DFR_VER_NI        0
 #define ARMV8_PMU_DFR_VER_V3P4      0x5
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 967ee7e8e408..dfc26992d14f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -49,6 +49,7 @@
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
+#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1cad7368aedf..53931a2e525f 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -804,6 +804,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_pmu_handle_pmcr(vcpu,
 					    __vcpu_sys_reg(vcpu, PMCR_EL0));
 
+		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
+			kvm_vcpu_pmu_restore_guest(vcpu);
+
 		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
 			return kvm_vcpu_suspend(vcpu);
 
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 560650972478..6b066e04dc5d 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -14,6 +14,7 @@
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
+#include <asm/arm_pmuv3.h>
 
 #define PERF_ATTR_CFG1_COUNTER_64BIT	BIT(0)
 
@@ -35,12 +36,8 @@ static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx)
 	return &vcpu->arch.pmu.pmc[cnt_idx];
 }
 
-static u32 kvm_pmu_event_mask(struct kvm *kvm)
+static u32 __kvm_pmu_event_mask(unsigned int pmuver)
 {
-	unsigned int pmuver;
-
-	pmuver = kvm->arch.arm_pmu->pmuver;
-
 	switch (pmuver) {
 	case ID_AA64DFR0_EL1_PMUVer_IMP:
 		return GENMASK(9, 0);
@@ -55,6 +52,14 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
 	}
 }
 
+static u32 kvm_pmu_event_mask(struct kvm *kvm)
+{
+	u64 dfr0 = IDREG(kvm, SYS_ID_AA64DFR0_EL1);
+	u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0);
+
+	return __kvm_pmu_event_mask(pmuver);
+}
+
 /**
  * kvm_pmc_is_64bit - determine if counter is 64bit
  * @pmc: counter context
@@ -672,8 +677,11 @@ void kvm_host_pmu_init(struct arm_pmu *pmu)
 {
 	struct arm_pmu_entry *entry;
 
-	if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
-	    pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+	/*
+	 * Check the sanitised PMU version for the system, as KVM does not
+	 * support implementations where PMUv3 exists on a subset of CPUs.
+	 */
+	if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit()))
 		return;
 
 	mutex_lock(&arm_pmus_lock);
@@ -750,11 +758,12 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	} else {
 		val = read_sysreg(pmceid1_el0);
 		/*
-		 * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled
+		 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
 		 * as RAZ
 		 */
-		if (vcpu->kvm->arch.arm_pmu->pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P4)
-			val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
+		val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
+			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
+			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
 		base = 32;
 	}
 
@@ -950,11 +959,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		return 0;
 	}
 	case KVM_ARM_VCPU_PMU_V3_FILTER: {
+		u8 pmuver = kvm_arm_pmu_get_pmuver_limit();
 		struct kvm_pmu_event_filter __user *uaddr;
 		struct kvm_pmu_event_filter filter;
 		int nr_events;
 
-		nr_events = kvm_pmu_event_mask(kvm) + 1;
+		/*
+		 * Allow userspace to specify an event filter for the entire
+		 * event range supported by PMUVer of the hardware, rather
+		 * than the guest's PMUVer for KVM backward compatibility.
+		 */
+		nr_events = __kvm_pmu_event_mask(pmuver) + 1;
 
 		uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;
 
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 121f1a14c829..0eea225fd09a 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -236,3 +236,21 @@ bool kvm_set_pmuserenr(u64 val)
 	ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val;
 	return true;
 }
+
+/*
+ * If we interrupted the guest to update the host PMU context, make
+ * sure we re-apply the guest EL0 state.
+ */
+void kvm_vcpu_pmu_resync_el0(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!has_vhe() || !in_interrupt())
+		return;
+
+	vcpu = kvm_get_running_vcpu();
+	if (!vcpu)
+		return;
+
+	kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu);
+}
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 08b3a1bf0ef6..6a3d8176f54a 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -772,6 +772,8 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+
+	kvm_vcpu_pmu_resync_el0();
 }
 
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 847da6fc2713..31029f4f7be8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -12,7 +12,7 @@
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 
-#ifdef CONFIG_HW_PERF_EVENTS
+#if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
 
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
@@ -74,6 +74,7 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 struct kvm_pmu_events *kvm_get_pmu_events(void);
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
+void kvm_vcpu_pmu_resync_el0(void);
 
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
@@ -171,6 +172,7 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
 	return 0;
 }
+static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
 #endif