RISC-V: KVM: Implement device interface for AIA irqchip

We implement KVM device interface for in-kernel AIA irqchip so that
user-space can use KVM device ioctls to create, configure, and destroy
in-kernel AIA irqchip.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>

arch/riscv/include/asm/kvm_aia.h

@@ -20,6 +20,33 @@ struct kvm_aia {
 
 	/* In-kernel irqchip initialized */
 	bool		initialized;
+
+	/* Virtualization mode (Emulation, HW Accelerated, or Auto) */
+	u32		mode;
+
+	/* Number of MSIs */
+	u32		nr_ids;
+
+	/* Number of wired IRQs */
+	u32		nr_sources;
+
+	/* Number of group bits in IMSIC address */
+	u32		nr_group_bits;
+
+	/* Position of group bits in IMSIC address */
+	u32		nr_group_shift;
+
+	/* Number of hart bits in IMSIC address */
+	u32		nr_hart_bits;
+
+	/* Number of guest bits in IMSIC address */
+	u32		nr_guest_bits;
+
+	/* Guest physical address of APLIC */
+	gpa_t		aplic_addr;
+
+	/* Internal state of APLIC */
+	void		*aplic_state;
 };
 
 struct kvm_vcpu_aia_csr {
@@ -38,8 +65,19 @@ struct kvm_vcpu_aia {
 
 	/* CPU AIA CSR context upon Guest VCPU reset */
 	struct kvm_vcpu_aia_csr guest_reset_csr;
+
+	/* Guest physical address of IMSIC for this VCPU */
+	gpa_t		imsic_addr;
+
+	/* HART index of IMSIC extacted from guest physical address */
+	u32		hart_index;
+
+	/* Internal state of IMSIC for this VCPU */
+	void		*imsic_state;
 };
 
+#define KVM_RISCV_AIA_UNDEF_ADDR	(-1)
+
 #define kvm_riscv_aia_initialized(k)	((k)->arch.aia.initialized)
 
 #define irqchip_in_kernel(k)		((k)->arch.aia.in_kernel)
@@ -50,10 +88,17 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 #define kvm_riscv_aia_available() \
 	static_branch_unlikely(&kvm_riscv_aia_available)
 
+extern struct kvm_device_ops kvm_riscv_aia_device_ops;
+
 static inline void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
 {
 }
 
+static inline int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 #define KVM_RISCV_AIA_IMSIC_TOPEI	(ISELECT_MASK + 1)
 static inline int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu,
 					       unsigned long isel,
@@ -64,6 +109,41 @@ static inline int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static inline void kvm_riscv_vcpu_aia_imsic_reset(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
+						  u32 guest_index, u32 offset,
+						  u32 iid)
+{
+	return 0;
+}
+
+static inline int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static inline void kvm_riscv_vcpu_aia_imsic_cleanup(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline int kvm_riscv_aia_aplic_inject(struct kvm *kvm,
+					     u32 source, bool level)
+{
+	return 0;
+}
+
+static inline int kvm_riscv_aia_aplic_init(struct kvm *kvm)
+{
+	return 0;
+}
+
+static inline void kvm_riscv_aia_aplic_cleanup(struct kvm *kvm)
+{
+}
+
 #ifdef CONFIG_32BIT
 void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu);
@@ -99,50 +179,18 @@ int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num,
 { .base = CSR_SIREG,      .count = 1, .func = kvm_riscv_vcpu_aia_rmw_ireg }, \
 { .base = CSR_STOPEI,     .count = 1, .func = kvm_riscv_vcpu_aia_rmw_topei },
 
-static inline int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu)
-{
-	return 1;
-}
-
-static inline void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu)
-{
-}
-
-static inline int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
-static inline void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu)
-{
-}
-
-static inline int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm,
-						 u32 hart_index,
-						 u32 guest_index, u32 iid)
-{
-	return 0;
-}
-
-static inline int kvm_riscv_aia_inject_msi(struct kvm *kvm,
-					   struct kvm_msi *msi)
-{
-	return 0;
-}
+int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu);
 
-static inline int kvm_riscv_aia_inject_irq(struct kvm *kvm,
-					   unsigned int irq, bool level)
-{
-	return 0;
-}
+int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index,
+				   u32 guest_index, u32 iid);
+int kvm_riscv_aia_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
+int kvm_riscv_aia_inject_irq(struct kvm *kvm, unsigned int irq, bool level);
 
-static inline void kvm_riscv_aia_init_vm(struct kvm *kvm)
-{
-}
-
-static inline void kvm_riscv_aia_destroy_vm(struct kvm *kvm)
-{
-}
+void kvm_riscv_aia_init_vm(struct kvm *kvm);
+void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
 
 int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
 			     void __iomem **hgei_va, phys_addr_t *hgei_pa);

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

@@ -204,6 +204,51 @@ enum KVM_RISCV_SBI_EXT_ID {
 #define KVM_REG_RISCV_SBI_MULTI_REG_LAST	\
 		KVM_REG_RISCV_SBI_MULTI_REG(KVM_RISCV_SBI_EXT_MAX - 1)
 
+/* Device Control API: RISC-V AIA */
+#define KVM_DEV_RISCV_APLIC_ALIGN		0x1000
+#define KVM_DEV_RISCV_APLIC_SIZE		0x4000
+#define KVM_DEV_RISCV_APLIC_MAX_HARTS		0x4000
+#define KVM_DEV_RISCV_IMSIC_ALIGN		0x1000
+#define KVM_DEV_RISCV_IMSIC_SIZE		0x1000
+
+#define KVM_DEV_RISCV_AIA_GRP_CONFIG		0
+#define KVM_DEV_RISCV_AIA_CONFIG_MODE		0
+#define KVM_DEV_RISCV_AIA_CONFIG_IDS		1
+#define KVM_DEV_RISCV_AIA_CONFIG_SRCS		2
+#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS	3
+#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT	4
+#define KVM_DEV_RISCV_AIA_CONFIG_HART_BITS	5
+#define KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS	6
+
+/*
+ * Modes of RISC-V AIA device:
+ * 1) EMUL (aka Emulation): Trap-n-emulate IMSIC
+ * 2) HWACCEL (aka HW Acceleration): Virtualize IMSIC using IMSIC guest files
+ * 3) AUTO (aka Automatic): Virtualize IMSIC using IMSIC guest files whenever
+ *    available otherwise fallback to trap-n-emulation
+ */
+#define KVM_DEV_RISCV_AIA_MODE_EMUL		0
+#define KVM_DEV_RISCV_AIA_MODE_HWACCEL		1
+#define KVM_DEV_RISCV_AIA_MODE_AUTO		2
+
+#define KVM_DEV_RISCV_AIA_IDS_MIN		63
+#define KVM_DEV_RISCV_AIA_IDS_MAX		2048
+#define KVM_DEV_RISCV_AIA_SRCS_MAX		1024
+#define KVM_DEV_RISCV_AIA_GROUP_BITS_MAX	8
+#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MIN	24
+#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MAX	56
+#define KVM_DEV_RISCV_AIA_HART_BITS_MAX		16
+#define KVM_DEV_RISCV_AIA_GUEST_BITS_MAX	8
+
+#define KVM_DEV_RISCV_AIA_GRP_ADDR		1
+#define KVM_DEV_RISCV_AIA_ADDR_APLIC		0
+#define KVM_DEV_RISCV_AIA_ADDR_IMSIC(__vcpu)	(1 + (__vcpu))
+#define KVM_DEV_RISCV_AIA_ADDR_MAX		\
+		(1 + KVM_DEV_RISCV_APLIC_MAX_HARTS)
+
+#define KVM_DEV_RISCV_AIA_GRP_CTRL		2
+#define KVM_DEV_RISCV_AIA_CTRL_INIT		0
+
 /* One single KVM irqchip, ie. the AIA */
 #define KVM_NR_IRQCHIPS			1
 

arch/riscv/kvm/Makefile

@@ -27,3 +27,4 @@ kvm-y += vcpu_sbi_hsm.o
 kvm-y += vcpu_timer.o
 kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o
 kvm-y += aia.o
+kvm-y += aia_device.o

arch/riscv/kvm/aia.c

@@ -631,6 +631,14 @@ int kvm_riscv_aia_init(void)
 	if (rc)
 		return rc;
 
+	/* Register device operations */
+	rc = kvm_register_device_ops(&kvm_riscv_aia_device_ops,
+				     KVM_DEV_TYPE_RISCV_AIA);
+	if (rc) {
+		aia_hgei_exit();
+		return rc;
+	}
+
 	/* Enable KVM AIA support */
 	static_branch_enable(&kvm_riscv_aia_available);
 
@@ -642,6 +650,9 @@ void kvm_riscv_aia_exit(void)
 	if (!kvm_riscv_aia_available())
 		return;
 
+	/* Unregister device operations */
+	kvm_unregister_device_ops(KVM_DEV_TYPE_RISCV_AIA);
+
 	/* Cleanup the HGEI state */
 	aia_hgei_exit();
 }

include/uapi/linux/kvm.h

@@ -1442,6 +1442,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
 	KVM_DEV_TYPE_ARM_PV_TIME,
 #define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
+	KVM_DEV_TYPE_RISCV_AIA,
+#define KVM_DEV_TYPE_RISCV_AIA		KVM_DEV_TYPE_RISCV_AIA
 	KVM_DEV_TYPE_MAX,
 };