[Backport] Added SBI v3.0 PMU enhancements in KVM and perf driver

arch/riscv/include/asm/kvm_vcpu_pmu.h

@@ -98,6 +98,9 @@ void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low,
 				      unsigned long saddr_high, unsigned long flags,
 				      struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low,
+				  unsigned long saddr_high, unsigned long num_events,
+				  unsigned long flags, struct kvm_vcpu_sbi_return *retdata);
 void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu);
 

arch/riscv/include/asm/kvm_vcpu_sbi.h

@@ -11,7 +11,7 @@
 
 #define KVM_SBI_IMPID 3
 
-#define KVM_SBI_VERSION_MAJOR 2
+#define KVM_SBI_VERSION_MAJOR 3
 #define KVM_SBI_VERSION_MINOR 0
 
 enum kvm_riscv_sbi_ext_status {

arch/riscv/include/asm/sbi.h

@@ -138,6 +138,7 @@ enum sbi_ext_pmu_fid {
 	SBI_EXT_PMU_COUNTER_FW_READ,
 	SBI_EXT_PMU_COUNTER_FW_READ_HI,
 	SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
+	SBI_EXT_PMU_EVENT_GET_INFO,
 };
 
 union sbi_pmu_ctr_info {
@@ -161,8 +162,21 @@ struct riscv_pmu_snapshot_data {
 	u64 reserved[447];
 };
 
+struct riscv_pmu_event_info {
+	u32 event_idx;
+	u32 output;
+	u64 event_data;
+};
+
+#define RISCV_PMU_EVENT_INFO_OUTPUT_MASK 0x01
+
 #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0)
+#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0)
+/* SBI v3.0 allows extended hpmeventX width value */
+#define RISCV_PMU_RAW_EVENT_V2_MASK GENMASK_ULL(55, 0)
 #define RISCV_PMU_RAW_EVENT_IDX 0x20000
+#define RISCV_PMU_RAW_EVENT_V2_IDX 0x30000
+#define RISCV_PLAT_FW_EVENT	0xFFFF
 
 /** General pmu event codes specified in SBI PMU extension */
 enum sbi_pmu_hw_generic_events_t {
@@ -219,6 +233,7 @@ enum sbi_pmu_event_type {
 	SBI_PMU_EVENT_TYPE_HW = 0x0,
 	SBI_PMU_EVENT_TYPE_CACHE = 0x1,
 	SBI_PMU_EVENT_TYPE_RAW = 0x2,
+	SBI_PMU_EVENT_TYPE_RAW_V2 = 0x3,
 	SBI_PMU_EVENT_TYPE_FW = 0xf,
 };
 

arch/riscv/kvm/vcpu_pmu.c

@@ -60,6 +60,7 @@ static u32 kvm_pmu_get_perf_event_type(unsigned long eidx)
 		type = PERF_TYPE_HW_CACHE;
 		break;
 	case SBI_PMU_EVENT_TYPE_RAW:
+	case SBI_PMU_EVENT_TYPE_RAW_V2:
 	case SBI_PMU_EVENT_TYPE_FW:
 		type = PERF_TYPE_RAW;
 		break;
@@ -128,6 +129,9 @@ static u64 kvm_pmu_get_perf_event_config(unsigned long eidx, uint64_t evt_data)
 	case SBI_PMU_EVENT_TYPE_RAW:
 		config = evt_data & RISCV_PMU_RAW_EVENT_MASK;
 		break;
+	case SBI_PMU_EVENT_TYPE_RAW_V2:
+		config = evt_data & RISCV_PMU_RAW_EVENT_V2_MASK;
+		break;
 	case SBI_PMU_EVENT_TYPE_FW:
 		if (ecode < SBI_PMU_FW_MAX)
 			config = (1ULL << 63) | ecode;
@@ -327,7 +331,7 @@ static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_att
 
 	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));
+		pr_debug("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
 		return PTR_ERR(event);
 	}
 
@@ -415,8 +419,6 @@ int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long s
 	int snapshot_area_size = sizeof(struct riscv_pmu_snapshot_data);
 	int sbiret = 0;
 	gpa_t saddr;
-	unsigned long hva;
-	bool writable;
 
 	if (!kvpmu || flags) {
 		sbiret = SBI_ERR_INVALID_PARAM;
@@ -438,19 +440,14 @@ int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long s
 		goto out;
 	}
 
-	hva = kvm_vcpu_gfn_to_hva_prot(vcpu, saddr >> PAGE_SHIFT, &writable);
-	if (kvm_is_error_hva(hva) || !writable) {
-		sbiret = SBI_ERR_INVALID_ADDRESS;
-		goto out;
-	}
-
 	kvpmu->sdata = kzalloc(snapshot_area_size, GFP_ATOMIC);
 	if (!kvpmu->sdata)
 		return -ENOMEM;
 
+	/* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */
 	if (kvm_vcpu_write_guest(vcpu, saddr, kvpmu->sdata, snapshot_area_size)) {
 		kfree(kvpmu->sdata);
-		sbiret = SBI_ERR_FAILURE;
+		sbiret = SBI_ERR_INVALID_ADDRESS;
 		goto out;
 	}
 
@@ -462,6 +459,62 @@ int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long s
 	return 0;
 }
 
+int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low,
+				  unsigned long saddr_high, unsigned long num_events,
+				  unsigned long flags, struct kvm_vcpu_sbi_return *retdata)
+{
+	struct riscv_pmu_event_info *einfo = NULL;
+	int shmem_size = num_events * sizeof(*einfo);
+	gpa_t shmem;
+	u32 eidx, etype;
+	u64 econfig;
+	int ret;
+
+	if (flags != 0 || (saddr_low & (SZ_16 - 1) || num_events == 0)) {
+		ret = SBI_ERR_INVALID_PARAM;
+		goto out;
+	}
+
+	shmem = saddr_low;
+	if (saddr_high != 0) {
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			shmem |= ((gpa_t)saddr_high << 32);
+		} else {
+			ret = SBI_ERR_INVALID_ADDRESS;
+			goto out;
+		}
+	}
+
+	einfo = kzalloc(shmem_size, GFP_KERNEL);
+	if (!einfo)
+		return -ENOMEM;
+
+	ret = kvm_vcpu_read_guest(vcpu, shmem, einfo, shmem_size);
+	if (ret) {
+		ret = SBI_ERR_FAILURE;
+		goto free_mem;
+	}
+
+	for (int i = 0; i < num_events; i++) {
+		eidx = einfo[i].event_idx;
+		etype = kvm_pmu_get_perf_event_type(eidx);
+		econfig = kvm_pmu_get_perf_event_config(eidx, einfo[i].event_data);
+		ret = riscv_pmu_get_event_info(etype, econfig, NULL);
+		einfo[i].output = (ret > 0) ? 1 : 0;
+	}
+
+	ret = kvm_vcpu_write_guest(vcpu, shmem, einfo, shmem_size);
+	if (ret)
+		ret = SBI_ERR_INVALID_ADDRESS;
+
+free_mem:
+	kfree(einfo);
+out:
+	retdata->err_val = ret;
+
+	return 0;
+}
+
 int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu,
 				struct kvm_vcpu_sbi_return *retdata)
 {

arch/riscv/kvm/vcpu_sbi_pmu.c

@@ -73,6 +73,9 @@ static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case SBI_EXT_PMU_SNAPSHOT_SET_SHMEM:
 		ret = kvm_riscv_vcpu_pmu_snapshot_set_shmem(vcpu, cp->a0, cp->a1, cp->a2, retdata);
 		break;
+	case SBI_EXT_PMU_EVENT_GET_INFO:
+		ret = kvm_riscv_vcpu_pmu_event_info(vcpu, cp->a0, cp->a1, cp->a2, cp->a3, retdata);
+		break;
 	default:
 		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 	}

arch/riscv/kvm/vcpu_sbi_sta.c

@@ -81,8 +81,6 @@ static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
 	unsigned long shmem_phys_hi = cp->a1;
 	u32 flags = cp->a2;
 	struct sbi_sta_struct zero_sta = {0};
-	unsigned long hva;
-	bool writable;
 	gpa_t shmem;
 	int ret;
 
@@ -107,13 +105,10 @@ static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
 			return SBI_ERR_INVALID_ADDRESS;
 	}
 
-	hva = kvm_vcpu_gfn_to_hva_prot(vcpu, shmem >> PAGE_SHIFT, &writable);
-	if (kvm_is_error_hva(hva) || !writable)
-		return SBI_ERR_INVALID_ADDRESS;
-
+	/* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */
 	ret = kvm_vcpu_write_guest(vcpu, shmem, &zero_sta, sizeof(zero_sta));
 	if (ret)
-		return SBI_ERR_FAILURE;
+		return SBI_ERR_INVALID_ADDRESS;
 
 	vcpu->arch.sta.shmem = shmem;
 	vcpu->arch.sta.last_steal = current->sched_info.run_delay;

drivers/perf/riscv_pmu_legacy.c

@@ -22,13 +22,13 @@ static int pmu_legacy_ctr_get_idx(struct perf_event *event)
 	struct perf_event_attr *attr = &event->attr;
 
 	if (event->attr.type != PERF_TYPE_HARDWARE)
-		return -EOPNOTSUPP;
+		return -ENOENT;
 	if (attr->config == PERF_COUNT_HW_CPU_CYCLES)
 		return RISCV_PMU_LEGACY_CYCLE;
 	else if (attr->config == PERF_COUNT_HW_INSTRUCTIONS)
 		return RISCV_PMU_LEGACY_INSTRET;
 	else
-		return -EOPNOTSUPP;
+		return -ENOENT;
 }
 
 /* For legacy config & counter index are same */