RISC-V: KVM: Add perf sampling support for guests

KVM enables perf for guest via counter virtualization. However, the
sampling can not be supported as there is no mechanism to enabled
trap/emulate scountovf in ISA yet. Rely on the SBI PMU snapshot
to provide the counter overflow data via the shared memory.

In case of sampling event, the host first sets the guest's LCOFI
interrupt and injects to the guest via irq filtering mechanism defined
in AIA specification. Thus, ssaia must be enabled in the host in order
to use perf sampling in the guest. No other AIA dependency w.r.t kernel
is required.
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Atish Patra <atishp@rivosinc.com>
Link: https://lore.kernel.org/r/20240420151741.962500-15-atishp@rivosinc.comSigned-off-by: Anup Patel <anup@brainfault.org>

arch/riscv/include/asm/csr.h

@@ -168,7 +168,8 @@
 #define VSIP_TO_HVIP_SHIFT	(IRQ_VS_SOFT - IRQ_S_SOFT)
 #define VSIP_VALID_MASK		((_AC(1, UL) << IRQ_S_SOFT) | \
 				 (_AC(1, UL) << IRQ_S_TIMER) | \
-				 (_AC(1, UL) << IRQ_S_EXT))
+				 (_AC(1, UL) << IRQ_S_EXT) | \
+				 (_AC(1, UL) << IRQ_PMU_OVF))
 
 /* AIA CSR bits */
 #define TOPI_IID_SHIFT		16

arch/riscv/include/asm/kvm_vcpu_pmu.h

@@ -36,6 +36,7 @@ struct kvm_pmc {
 	bool started;
 	/* Monitoring event ID */
 	unsigned long event_idx;
+	struct kvm_vcpu *vcpu;
 };
 
 /* PMU data structure per vcpu */
@@ -50,6 +51,8 @@ struct kvm_pmu {
 	bool init_done;
 	/* Bit map of all the virtual counter used */
 	DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS);
+	/* Bit map of all the virtual counter overflown */
+	DECLARE_BITMAP(pmc_overflown, RISCV_KVM_MAX_COUNTERS);
 	/* The address of the counter snapshot area (guest physical address) */
 	gpa_t snapshot_addr;
 	/* The actual data of the snapshot */

arch/riscv/include/uapi/asm/kvm.h

@@ -167,6 +167,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZFA,
 	KVM_RISCV_ISA_EXT_ZTSO,
 	KVM_RISCV_ISA_EXT_ZACAS,
+	KVM_RISCV_ISA_EXT_SSCOFPMF,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 

arch/riscv/kvm/aia.c

@@ -545,6 +545,9 @@ void kvm_riscv_aia_enable(void)
 	enable_percpu_irq(hgei_parent_irq,
 			  irq_get_trigger_type(hgei_parent_irq));
 	csr_set(CSR_HIE, BIT(IRQ_S_GEXT));
+	/* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */
+	if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF))
+		csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF));
 }
 
 void kvm_riscv_aia_disable(void)
@@ -558,6 +561,8 @@ void kvm_riscv_aia_disable(void)
 		return;
 	hgctrl = get_cpu_ptr(&aia_hgei);
 
+	if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF))
+		csr_clear(CSR_HVIEN, BIT(IRQ_PMU_OVF));
 	/* Disable per-CPU SGEI interrupt */
 	csr_clear(CSR_HIE, BIT(IRQ_S_GEXT));
 	disable_percpu_irq(hgei_parent_irq);

arch/riscv/kvm/vcpu.c

@@ -373,6 +373,13 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	/* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */
+	if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) {
+		if (!(hvip & (1UL << IRQ_PMU_OVF)) &&
+		    !test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask))
+			clear_bit(IRQ_PMU_OVF, v->irqs_pending);
+	}
+
 	/* Sync-up AIA high interrupts */
 	kvm_riscv_vcpu_aia_sync_interrupts(vcpu);
 
@@ -390,7 +397,8 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 	if (irq < IRQ_LOCAL_MAX &&
 	    irq != IRQ_VS_SOFT &&
 	    irq != IRQ_VS_TIMER &&
-	    irq != IRQ_VS_EXT)
+	    irq != IRQ_VS_EXT &&
+	    irq != IRQ_PMU_OVF)
 		return -EINVAL;
 
 	set_bit(irq, vcpu->arch.irqs_pending);
@@ -405,14 +413,15 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 {
 	/*
-	 * We only allow VS-mode software, timer, and external
+	 * We only allow VS-mode software, timer, counter overflow and external
 	 * interrupts when irq is one of the local interrupts
 	 * defined by RISC-V privilege specification.
 	 */
 	if (irq < IRQ_LOCAL_MAX &&
 	    irq != IRQ_VS_SOFT &&
 	    irq != IRQ_VS_TIMER &&
-	    irq != IRQ_VS_EXT)
+	    irq != IRQ_VS_EXT &&
+	    irq != IRQ_PMU_OVF)
 		return -EINVAL;
 
 	clear_bit(irq, vcpu->arch.irqs_pending);

arch/riscv/kvm/vcpu_onereg.c

@@ -36,6 +36,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	/* Multi letter extensions (alphabetically sorted) */
 	KVM_ISA_EXT_ARR(SMSTATEEN),
 	KVM_ISA_EXT_ARR(SSAIA),
+	KVM_ISA_EXT_ARR(SSCOFPMF),
 	KVM_ISA_EXT_ARR(SSTC),
 	KVM_ISA_EXT_ARR(SVINVAL),
 	KVM_ISA_EXT_ARR(SVNAPOT),
@@ -99,6 +100,9 @@ static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
 	switch (ext) {
 	case KVM_RISCV_ISA_EXT_H:
 		return false;
+	case KVM_RISCV_ISA_EXT_SSCOFPMF:
+		/* Sscofpmf depends on interrupt filtering defined in ssaia */
+		return __riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSAIA);
 	case KVM_RISCV_ISA_EXT_V:
 		return riscv_v_vstate_ctrl_user_allowed();
 	default:
@@ -116,6 +120,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_C:
 	case KVM_RISCV_ISA_EXT_I:
 	case KVM_RISCV_ISA_EXT_M:
+	/* There is not architectural config bit to disable sscofpmf completely */
+	case KVM_RISCV_ISA_EXT_SSCOFPMF:
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:

arch/riscv/kvm/vcpu_pmu.c

@@ -230,6 +230,47 @@ static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ct
 	return 0;
 }
 
+static void kvm_riscv_pmu_overflow(struct perf_event *perf_event,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct kvm_vcpu *vcpu = pmc->vcpu;
+	struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu);
+	struct riscv_pmu *rpmu = to_riscv_pmu(perf_event->pmu);
+	u64 period;
+
+	/*
+	 * Stop the event counting by directly accessing the perf_event.
+	 * Otherwise, this needs to deferred via a workqueue.
+	 * That will introduce skew in the counter value because the actual
+	 * physical counter would start after returning from this function.
+	 * It will be stopped again once the workqueue is scheduled
+	 */
+	rpmu->pmu.stop(perf_event, PERF_EF_UPDATE);
+
+	/*
+	 * The hw counter would start automatically when this function returns.
+	 * Thus, the host may continue to interrupt and inject it to the guest
+	 * even without the guest configuring the next event. Depending on the hardware
+	 * the host may have some sluggishness only if privilege mode filtering is not
+	 * available. In an ideal world, where qemu is not the only capable hardware,
+	 * this can be removed.
+	 * FYI: ARM64 does this way while x86 doesn't do anything as such.
+	 * TODO: Should we keep it for RISC-V ?
+	 */
+	period = -(local64_read(&perf_event->count));
+
+	local64_set(&perf_event->hw.period_left, 0);
+	perf_event->attr.sample_period = period;
+	perf_event->hw.sample_period = period;
+
+	set_bit(pmc->idx, kvpmu->pmc_overflown);
+	kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_PMU_OVF);
+
+	rpmu->pmu.start(perf_event, PERF_EF_RELOAD);
+}
+
 static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr,
 				      unsigned long flags, unsigned long eidx,
 				      unsigned long evtdata)
@@ -249,7 +290,7 @@ static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_att
 	 */
 	attr->sample_period = kvm_pmu_get_sample_period(pmc);
 
-	event = perf_event_create_kernel_counter(attr, -1, current, NULL, pmc);
+	event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc);
 	if (IS_ERR(event)) {
 		pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
 		return PTR_ERR(event);
@@ -443,6 +484,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 		pmc_index = i + ctr_base;
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
 			continue;
+		/* The guest started the counter again. Reset the overflow status */
+		clear_bit(pmc_index, kvpmu->pmc_overflown);
 		pmc = &kvpmu->pmc[pmc_index];
 		if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) {
 			pmc->counter_val = ival;
@@ -546,7 +589,13 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 			else if (pmc->perf_event)
 				pmc->counter_val += perf_event_read_value(pmc->perf_event,
 									  &enabled, &running);
-			/* TODO: Add counter overflow support when sscofpmf support is added */
+			/*
+			 * The counter and overflow indicies in the snapshot region are w.r.to
+			 * cbase. Modify the set bit in the counter mask instead of the pmc_index
+			 * which indicates the absolute counter index.
+			 */
+			if (test_bit(pmc_index, kvpmu->pmc_overflown))
+				kvpmu->sdata->ctr_overflow_mask |= BIT(i);
 			kvpmu->sdata->ctr_values[i] = pmc->counter_val;
 			shmem_needs_update = true;
 		}
@@ -554,6 +603,15 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 		if (flags & SBI_PMU_STOP_FLAG_RESET) {
 			pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID;
 			clear_bit(pmc_index, kvpmu->pmc_in_use);
+			clear_bit(pmc_index, kvpmu->pmc_overflown);
+			if (snap_flag_set) {
+				/*
+				 * Only clear the given counter as the caller is responsible to
+				 * validate both the overflow mask and configured counters.
+				 */
+				kvpmu->sdata->ctr_overflow_mask &= ~BIT(i);
+				shmem_needs_update = true;
+			}
 		}
 	}
 
@@ -703,6 +761,7 @@ void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu)
 		pmc = &kvpmu->pmc[i];
 		pmc->idx = i;
 		pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID;
+		pmc->vcpu = vcpu;
 		if (i < kvpmu->num_hw_ctrs) {
 			pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW;
 			if (i < 3)
@@ -735,13 +794,14 @@ void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu)
 	if (!kvpmu)
 		return;
 
-	for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_MAX_COUNTERS) {
+	for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS) {
 		pmc = &kvpmu->pmc[i];
 		pmc->counter_val = 0;
 		kvm_pmu_release_perf_event(pmc);
 		pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID;
 	}
-	bitmap_zero(kvpmu->pmc_in_use, RISCV_MAX_COUNTERS);
+	bitmap_zero(kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS);
+	bitmap_zero(kvpmu->pmc_overflown, RISCV_KVM_MAX_COUNTERS);
 	memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event));
 	kvm_pmu_clear_snapshot_area(vcpu);
 }