KVM GICv3 emulation

index 66ce176..c528615 100644
@@ -23,6 +23,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/kvm_arm.h>
+#include <asm/cputype.h>
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);

@@ -167,9 +168,9 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
 }
 
-static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cp15[c0_MPIDR];
+	return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)

index 254e065..a4e1155 100644
@@ -234,6 +234,8 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}

index 2d6d910..d0fadd6 100644
@@ -1045,6 +1045,19 @@ static void check_kvm_target_cpu(void *ret)
 	*(int *)ret = kvm_target_cpu();
 }
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	mpidr &= MPIDR_HWID_BITMASK;
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
+			return vcpu;
+	}
+	return NULL;
+}
+
 /**
  * Initialize Hyp-mode and memory mappings on all CPUs.
  */

index 58cb324..02fa8ef 100644
@@ -22,6 +22,7 @@
 #include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_psci.h>
+#include <asm/kvm_host.h>
 
 /*
  * This is an implementation of the Power State Coordination Interface

@@ -66,25 +67,17 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
-	struct kvm_vcpu *vcpu = NULL, *tmp;
+	struct kvm_vcpu *vcpu = NULL;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
-	unsigned long mpidr;
 	phys_addr_t target_pc;
-	int i;
 
-	cpu_id = *vcpu_reg(source_vcpu, 1);
+	cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
-	kvm_for_each_vcpu(i, tmp, kvm) {
-		mpidr = kvm_vcpu_get_mpidr(tmp);
-		if ((mpidr & MPIDR_HWID_BITMASK) == (cpu_id & MPIDR_HWID_BITMASK)) {
-			vcpu = tmp;
-			break;
-		}
-	}
+	vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
 
 	/*
 	 * Make sure the caller requested a valid CPU and that the CPU is

@@ -155,7 +148,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	 * then ON else OFF
 	 */
 	kvm_for_each_vcpu(i, tmp, kvm) {
-		mpidr = kvm_vcpu_get_mpidr(tmp);
+		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if (((mpidr & target_affinity_mask) == target_affinity) &&
 		    !tmp->arch.pause) {
 			return PSCI_0_2_AFFINITY_LEVEL_ON;

index 8127e45..fc3459f 100644
@@ -27,6 +27,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
+#include <asm/cputype.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);

@@ -187,9 +188,9 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
 }
 
-static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_sys_reg(vcpu, MPIDR_EL1);
+	return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)

index 0b7dfdb..37c4ff1 100644
@@ -206,6 +206,8 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 				       phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,

index 3d7c2df..136e679 100644
@@ -252,10 +252,19 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
+	u64 mpidr;
+
 	/*
-	 * Simply map the vcpu_id into the Aff0 field of the MPIDR.
+	 * Map the vcpu_id into the first three affinity level fields of
+	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
+	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
+	 * of the GICv3 to be able to address each CPU directly when
+	 * sending IPIs.
 	 */
-	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
+	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
+	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
+	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
+	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
 }
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */

index d0fadd6..dd1a689 100644
@@ -821,7 +821,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
 		if (vgic_present)
-			return kvm_vgic_create(kvm);
+			return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 		else
 			return -ENXIO;
 	}

index ac4888d..525ce42 100644
@@ -140,6 +140,9 @@ struct vgic_dist {
 	bool			in_kernel;
 	bool			ready;
 
+	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
+	u32			vgic_model;
+
 	int			nr_cpus;
 	int			nr_irqs;
 

@@ -275,7 +278,7 @@ struct kvm_exit_mmio;
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_create(struct kvm *kvm);
+int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);

@@ -327,7 +330,7 @@ static inline int kvm_vgic_map_resources(struct kvm *kvm)
 	return 0;
 }
 
-static inline int kvm_vgic_create(struct kvm *kvm)
+static inline int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
 	return 0;
 }

index c84f53df..6215e76 100644
@@ -1935,7 +1935,7 @@ out:
 	return ret;
 }
 
-int kvm_vgic_create(struct kvm *kvm)
+int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
 	int i, vcpu_lock_idx = -1, ret;
 	struct kvm_vcpu *vcpu;

@@ -1967,6 +1967,7 @@ int kvm_vgic_create(struct kvm *kvm)
 
 	spin_lock_init(&kvm->arch.vgic.lock);
 	kvm->arch.vgic.in_kernel = true;
+	kvm->arch.vgic.vgic_model = type;
 	kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;

@@ -2404,7 +2405,7 @@ static void vgic_destroy(struct kvm_device *dev)
 
 static int vgic_create(struct kvm_device *dev, u32 type)
 {
-	return kvm_vgic_create(dev->kvm);
+	return kvm_vgic_create(dev->kvm, type);
 }
 
 static struct kvm_device_ops kvm_arm_vgic_v2_ops = {

index 6215e76..0bb0b9b 100644
@@ -1034,36 +1034,27 @@ static bool vgic_validate_access(const struct vgic_dist *dist,
 }
 
 /**
- * vgic_handle_mmio - handle an in-kernel MMIO access
+ * vgic_handle_mmio_range - handle an in-kernel MMIO access
  * @vcpu:	pointer to the vcpu performing the access
  * @run:	pointer to the kvm_run structure
  * @mmio:	pointer to the data describing the access
+ * @ranges:	array of MMIO ranges in a given region
+ * @mmio_base:	base address of that region
  *
- * returns true if the MMIO access has been performed in kernel space,
- * and false if it needs to be emulated in user space.
+ * returns true if the MMIO access could be performed
  */
-bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		      struct kvm_exit_mmio *mmio)
+static bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			    struct kvm_exit_mmio *mmio,
+			    const struct mmio_range *ranges,
+			    unsigned long mmio_base)
 {
 	const struct mmio_range *range;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long base = dist->vgic_dist_base;
 	bool updated_state;
 	unsigned long offset;
 
-	if (!irqchip_in_kernel(vcpu->kvm) ||
-	    mmio->phys_addr < base ||
-	    (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE))
-		return false;
-
-	/* We don't support ldrd / strd or ldm / stm to the emulated vgic */
-	if (mmio->len > 4) {
-		kvm_inject_dabt(vcpu, mmio->phys_addr);
-		return true;
-	}
-
-	offset = mmio->phys_addr - base;
-	range = find_matching_range(vgic_dist_ranges, mmio, offset);
+	offset = mmio->phys_addr - mmio_base;
+	range = find_matching_range(ranges, mmio, offset);
 	if (unlikely(!range || !range->handle_mmio)) {
 		pr_warn("Unhandled access %d %08llx %d\n",
 			mmio->is_write, mmio->phys_addr, mmio->len);

@@ -1071,7 +1062,7 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	}
 
 	spin_lock(&vcpu->kvm->arch.vgic.lock);
-	offset = mmio->phys_addr - range->base - base;
+	offset -= range->base;
 	if (vgic_validate_access(dist, range, offset)) {
 		updated_state = range->handle_mmio(vcpu, mmio, offset);
 	} else {

@@ -1089,6 +1080,48 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	return true;
 }
 
+static inline bool is_in_range(phys_addr_t addr, unsigned long len,
+			       phys_addr_t baseaddr, unsigned long size)
+{
+	return (addr >= baseaddr) && (addr + len <= baseaddr + size);
+}
+
+static bool vgic_v2_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				struct kvm_exit_mmio *mmio)
+{
+	unsigned long base = vcpu->kvm->arch.vgic.vgic_dist_base;
+
+	if (!is_in_range(mmio->phys_addr, mmio->len, base,
+			 KVM_VGIC_V2_DIST_SIZE))
+		return false;
+
+	/* GICv2 does not support accesses wider than 32 bits */
+	if (mmio->len > 4) {
+		kvm_inject_dabt(vcpu, mmio->phys_addr);
+		return true;
+	}
+
+	return vgic_handle_mmio_range(vcpu, run, mmio, vgic_dist_ranges, base);
+}
+
+/**
+ * vgic_handle_mmio - handle an in-kernel MMIO access for the GIC emulation
+ * @vcpu:      pointer to the vcpu performing the access
+ * @run:       pointer to the kvm_run structure
+ * @mmio:      pointer to the data describing the access
+ *
+ * returns true if the MMIO access has been performed in kernel space,
+ * and false if it needs to be emulated in user space.
+ */
+bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		      struct kvm_exit_mmio *mmio)
+{
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return false;
+
+	return vgic_v2_handle_mmio(vcpu, run, mmio);
+}
+
 static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
 {
 	return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;

index 0bb0b9b..2a69bc7 100644
@@ -1033,6 +1033,53 @@ static bool vgic_validate_access(const struct vgic_dist *dist,
 	return true;
 }
 
+/*
+ * Call the respective handler function for the given range.
+ * We split up any 64 bit accesses into two consecutive 32 bit
+ * handler calls and merge the result afterwards.
+ * We do this in a little endian fashion regardless of the host's
+ * or guest's endianness, because the GIC is always LE and the rest of
+ * the code (vgic_reg_access) also puts it in a LE fashion already.
+ * At this point we have already identified the handle function, so
+ * range points to that one entry and offset is relative to this.
+ */
+static bool call_range_handler(struct kvm_vcpu *vcpu,
+			       struct kvm_exit_mmio *mmio,
+			       unsigned long offset,
+			       const struct mmio_range *range)
+{
+	u32 *data32 = (void *)mmio->data;
+	struct kvm_exit_mmio mmio32;
+	bool ret;
+
+	if (likely(mmio->len <= 4))
+		return range->handle_mmio(vcpu, mmio, offset);
+
+	/*
+	 * Any access bigger than 4 bytes (that we currently handle in KVM)
+	 * is actually 8 bytes long, caused by a 64-bit access
+	 */
+
+	mmio32.len = 4;
+	mmio32.is_write = mmio->is_write;
+
+	mmio32.phys_addr = mmio->phys_addr + 4;
+	if (mmio->is_write)
+		*(u32 *)mmio32.data = data32[1];
+	ret = range->handle_mmio(vcpu, &mmio32, offset + 4);
+	if (!mmio->is_write)
+		data32[1] = *(u32 *)mmio32.data;
+
+	mmio32.phys_addr = mmio->phys_addr;
+	if (mmio->is_write)
+		*(u32 *)mmio32.data = data32[0];
+	ret |= range->handle_mmio(vcpu, &mmio32, offset);
+	if (!mmio->is_write)
+		data32[0] = *(u32 *)mmio32.data;
+
+	return ret;
+}
+
 /**
  * vgic_handle_mmio_range - handle an in-kernel MMIO access
  * @vcpu:	pointer to the vcpu performing the access

@@ -1064,10 +1111,10 @@ static bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	spin_lock(&vcpu->kvm->arch.vgic.lock);
 	offset -= range->base;
 	if (vgic_validate_access(dist, range, offset)) {
-		updated_state = range->handle_mmio(vcpu, mmio, offset);
+		updated_state = call_range_handler(vcpu, mmio, offset, range);
 	} else {
-		vgic_reg_access(mmio, NULL, offset,
-				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+		if (!mmio->is_write)
+			memset(mmio->data, 0, mmio->len);
 		updated_state = false;
 	}
 	spin_unlock(&vcpu->kvm->arch.vgic.lock);

index 525ce42..dd24396 100644
@@ -134,6 +134,15 @@ struct vgic_params {
 	void __iomem	*vctrl_base;
 };
 
+struct vgic_vm_ops {
+	bool	(*handle_mmio)(struct kvm_vcpu *, struct kvm_run *,
+			       struct kvm_exit_mmio *);
+	bool	(*queue_sgi)(struct kvm_vcpu *, int irq);
+	void	(*add_sgi_source)(struct kvm_vcpu *, int irq, int source);
+	int	(*init_model)(struct kvm *);
+	int	(*map_resources)(struct kvm *, const struct vgic_params *);
+};
+
 struct vgic_dist {
 #ifdef CONFIG_KVM_ARM_VGIC
 	spinlock_t		lock;

@@ -215,6 +224,8 @@ struct vgic_dist {
 
 	/* Bitmap indicating which CPU has something pending */
 	unsigned long		*irq_pending_on_cpu;
+
+	struct vgic_vm_ops	vm_ops;
 #endif
 };
 

176 lines not on this page · raw message

index 26f1060..703eeed 100644
@@ -1042,6 +1042,7 @@ void kvm_unregister_device_ops(u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
+extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 

index 2935405..e1cd3cb 100644
@@ -229,6 +229,8 @@ int vgic_v2_probe(struct device_node *vgic_node,
 		goto out_unmap;
 	}
 
+	kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2);
+
 	vgic->vcpu_base = vcpu_res.start;
 
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,

index 1c2c8ee..d14c75f 100644
@@ -230,6 +230,7 @@ int vgic_v3_probe(struct device_node *vgic_node,
 		ret = -ENXIO;
 		goto out;
 	}
+	kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2);
 
 	vgic->vcpu_base = vcpu_res.start;
 	vgic->vctrl_base = NULL;

index 205df80..038d287 100644
@@ -2559,7 +2559,7 @@ static int vgic_create(struct kvm_device *dev, u32 type)
 	return kvm_vgic_create(dev->kvm, type);
 }
 
-static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.name = "kvm-arm-vgic",
 	.create = vgic_create,
 	.destroy = vgic_destroy,

@@ -2638,8 +2638,7 @@ int kvm_vgic_hyp_init(void)
 
 	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
 
-	return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
-				       KVM_DEV_TYPE_ARM_VGIC_V2);
+	return 0;
 
 out_free_irq:
 	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());

index 038d287..73cc18e 100644
@@ -2089,7 +2089,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 
 	mutex_lock(&kvm->lock);
 
-	if (kvm->arch.vgic.vctrl_base) {
+	if (irqchip_in_kernel(kvm)) {
 		ret = -EEXIST;
 		goto out;
 	}

index a4e1155..60c52ad 100644
@@ -68,6 +68,7 @@ struct kvm_arch {
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
+	int max_vcpus;
 };
 
 #define KVM_NR_MEM_OBJS     40

index dd1a689..c33e4ab 100644
@@ -132,6 +132,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* Mark the initial VMID generation invalid */
 	kvm->arch.vmid_gen = 0;
 
+	/* The maximum number of VCPUs is limited by the host's GIC model */
+	kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus();
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(kvm);

@@ -218,6 +221,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	if (id >= kvm->arch.max_vcpus) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;

index 37c4ff1..544de35 100644
@@ -59,6 +59,9 @@ struct kvm_arch {
 	/* VTTBR value associated with above pgd and vmid */
 	u64    vttbr;
 
+	/* The maximum number of vCPUs depends on the used GIC model */
+	int max_vcpus;
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 

index dd24396..1c0e9db 100644
@@ -33,6 +33,7 @@
 #define VGIC_V2_MAX_LRS		(1 << 6)
 #define VGIC_V3_MAX_LRS		16
 #define VGIC_MAX_IRQS		1024
+#define VGIC_V2_MAX_CPUS	8
 
 /* Sanity checks... */
 #if (KVM_MAX_VCPUS > 8)

@@ -132,6 +133,7 @@ struct vgic_params {
 	unsigned int	maint_irq;
 	/* Virtual control interface base address */
 	void __iomem	*vctrl_base;
+	int		max_gic_vcpus;
 };
 
 struct vgic_vm_ops {

@@ -289,6 +291,7 @@ struct kvm_exit_mmio;
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_get_max_vcpus(void);
 int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);

@@ -393,6 +396,11 @@ static inline bool vgic_ready(struct kvm *kvm)
 {
 	return true;
 }
+
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+	return KVM_MAX_VCPUS;
+}
 #endif
 
 #endif

index e1cd3cb..e8b82b2 100644
@@ -237,6 +237,7 @@ int vgic_v2_probe(struct device_node *vgic_node,
 		 vctrl_res.start, vgic->maint_irq);
 
 	vgic->type = VGIC_V2;
+	vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
 	*ops = &vgic_v2_ops;
 	*params = vgic;
 	goto out;

index d14c75f..ea39bad 100644
@@ -235,6 +235,7 @@ int vgic_v3_probe(struct device_node *vgic_node,
 	vgic->vcpu_base = vcpu_res.start;
 	vgic->vctrl_base = NULL;
 	vgic->type = VGIC_V3;
+	vgic->max_gic_vcpus = KVM_MAX_VCPUS;
 
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
 		 vcpu_res.start, vgic->maint_irq);

index 73cc18e..2bfaf53 100644
@@ -1868,6 +1868,17 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 	return 0;
 }
 
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+int kvm_vgic_get_max_vcpus(void)
+{
+	return vgic->max_gic_vcpus;
+}
+
 void kvm_vgic_destroy(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;

@@ -2063,6 +2074,8 @@ static int vgic_v2_init_emulation(struct kvm *kvm)
 	dist->vm_ops.init_model = vgic_v2_init_model;
 	dist->vm_ops.map_resources = vgic_v2_map_resources;
 
+	kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS;
+
 	return 0;
 }
 

@@ -2079,6 +2092,15 @@ static int init_vgic_model(struct kvm *kvm, int type)
 		break;
 	}
 
+	if (ret)
+		return ret;
+
+	if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus) {
+		pr_warn_ratelimited("VGIC model only supports up to %d vCPUs\n",
+			kvm->arch.max_vcpus);
+		ret = -EINVAL;
+	}
+
 	return ret;
 }
 

index 9a9fce0..9d34486 100644
@@ -140,6 +140,7 @@ int main(void)
   DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
   DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
   DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
+  DEFINE(VGIC_V3_CPU_SRE,	offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
   DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
   DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
   DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));

index 1c0e9db..ff04afd 100644
@@ -245,6 +245,7 @@ struct vgic_v3_cpu_if {
 #ifdef CONFIG_ARM_GIC_V3
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
+	u32		vgic_sre;	/* Restored only, change ignored */
 	u32		vgic_misr;	/* Saved only */
 	u32		vgic_eisr;	/* Saved only */
 	u32		vgic_elrsr;	/* Saved only */

index ea39bad..5249048 100644
@@ -145,15 +145,19 @@ static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 
 static void vgic_v3_enable(struct kvm_vcpu *vcpu)
 {
+	struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
+
 	/*
 	 * By forcing VMCR to zero, the GIC will restore the binary
 	 * points to their reset values. Anything else resets to zero
 	 * anyway.
 	 */
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = 0;
+	vgic_v3->vgic_vmcr = 0;
+
+	vgic_v3->vgic_sre = 0;
 
 	/* Get the show on the road... */
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr = ICH_HCR_EN;
+	vgic_v3->vgic_hcr = ICH_HCR_EN;
 }
 
 static const struct vgic_ops vgic_v3_ops = {

index 2bfaf53..11f350e 100644
@@ -492,64 +492,66 @@ static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
+static bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
+				   phys_addr_t offset, int vcpu_id, int access)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
-				       vcpu->vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+	u32 *reg;
+	int mode = ACCESS_READ_VALUE | access;
+	struct kvm_vcpu *target_vcpu = kvm_get_vcpu(kvm, vcpu_id);
+
+	reg = vgic_bitmap_get_reg(&kvm->arch.vgic.irq_enabled, vcpu_id, offset);
+	vgic_reg_access(mmio, reg, offset, mode);
 	if (mmio->is_write) {
-		vgic_update_state(vcpu->kvm);
+		if (access & ACCESS_WRITE_CLEARBIT) {
+			if (offset < 4) /* Force SGI enabled */
+				*reg |= 0xffff;
+			vgic_retire_disabled_irqs(target_vcpu);
+		}
+		vgic_update_state(kvm);
 		return true;
 	}
 
 	return false;
 }
 
+static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
+				       struct kvm_exit_mmio *mmio,
+				       phys_addr_t offset)
+{
+	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
+				      vcpu->vcpu_id, ACCESS_WRITE_SETBIT);
+}
+
 static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
 					 struct kvm_exit_mmio *mmio,
 					 phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
-				       vcpu->vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
-	if (mmio->is_write) {
-		if (offset < 4) /* Force SGI enabled */
-			*reg |= 0xffff;
-		vgic_retire_disabled_irqs(vcpu);
-		vgic_update_state(vcpu->kvm);
-		return true;
-	}
-
-	return false;
+	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
+				      vcpu->vcpu_id, ACCESS_WRITE_CLEARBIT);
 }
 
-static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
+static bool vgic_handle_set_pending_reg(struct kvm *kvm,
 					struct kvm_exit_mmio *mmio,
-					phys_addr_t offset)
+					phys_addr_t offset, int vcpu_id)
 {
 	u32 *reg, orig;
 	u32 level_mask;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT;
+	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset);
+	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu_id, offset);
 	level_mask = (~(*reg));
 
 	/* Mark both level and edge triggered irqs as pending */
-	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
 	orig = *reg;
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+	vgic_reg_access(mmio, reg, offset, mode);
 
 	if (mmio->is_write) {
 		/* Set the soft-pending flag only for level-triggered irqs */
 		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
-					  vcpu->vcpu_id, offset);
-		vgic_reg_access(mmio, reg, offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+					  vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset, mode);
 		*reg &= level_mask;
 
 		/* Ignore writes to SGIs */

@@ -558,31 +560,30 @@ static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
 			*reg |= orig & 0xffff;
 		}
 
-		vgic_update_state(vcpu->kvm);
+		vgic_update_state(kvm);
 		return true;
 	}
 
 	return false;
 }
 
-static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
+static bool vgic_handle_clear_pending_reg(struct kvm *kvm,
 					  struct kvm_exit_mmio *mmio,
-					  phys_addr_t offset)
+					  phys_addr_t offset, int vcpu_id)
 {
 	u32 *level_active;
 	u32 *reg, orig;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT;
+	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
 	orig = *reg;
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+	vgic_reg_access(mmio, reg, offset, mode);
 	if (mmio->is_write) {
 		/* Re-set level triggered level-active interrupts */
 		level_active = vgic_bitmap_get_reg(&dist->irq_level,
-					  vcpu->vcpu_id, offset);
-		reg = vgic_bitmap_get_reg(&dist->irq_pending,
-					  vcpu->vcpu_id, offset);
+					  vcpu_id, offset);
+		reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
 		*reg |= *level_active;
 
 		/* Ignore writes to SGIs */

@@ -593,17 +594,31 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
 
 		/* Clear soft-pending flags */
 		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
-					  vcpu->vcpu_id, offset);
-		vgic_reg_access(mmio, reg, offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+					  vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset, mode);
 
-		vgic_update_state(vcpu->kvm);
+		vgic_update_state(kvm);
 		return true;
 	}
-
 	return false;
 }
 
+static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
+					struct kvm_exit_mmio *mmio,
+					phys_addr_t offset)
+{
+	return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
+					   vcpu->vcpu_id);
+}
+
+static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
+					  struct kvm_exit_mmio *mmio,
+					  phys_addr_t offset)
+{
+	return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
+					     vcpu->vcpu_id);
+}
+
 static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
 				     struct kvm_exit_mmio *mmio,
 				     phys_addr_t offset)

@@ -726,14 +741,10 @@ static u16 vgic_cfg_compress(u32 val)
  * LSB is always 0. As such, we only keep the upper bit, and use the
  * two above functions to compress/expand the bits
  */
-static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
-				struct kvm_exit_mmio *mmio, phys_addr_t offset)
+static bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
+				phys_addr_t offset)
 {
 	u32 val;
-	u32 *reg;
-
-	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset >> 1);
 
 	if (offset & 4)
 		val = *reg >> 16;

@@ -762,6 +773,17 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
+				struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+	u32 *reg;
+
+	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
+				  vcpu->vcpu_id, offset >> 1);
+
+	return vgic_handle_cfg_reg(reg, mmio, offset);
+}
+
 static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
 				struct kvm_exit_mmio *mmio, phys_addr_t offset)
 {

index 11f350e..a74b380 100644
@@ -2441,7 +2441,8 @@ out:
 	return ret;
 }
 
-static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+static int vgic_set_common_attr(struct kvm_device *dev,
+				struct kvm_device_attr *attr)
 {
 	int r;
 

@@ -2457,17 +2458,6 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		r = kvm_vgic_addr(dev->kvm, type, &addr, true);
 		return (r == -ENODEV) ? -ENXIO : r;
 	}
-
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-		u32 reg;
-
-		if (get_user(reg, uaddr))
-			return -EFAULT;
-
-		return vgic_attr_regs_access(dev, attr, &reg, true);
-	}
 	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
 		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
 		u32 val;

@@ -2511,7 +2501,33 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return -ENXIO;
 }
 
-static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int ret;
+
+	ret = vgic_set_common_attr(dev, attr);
+	if (ret != -ENXIO)
+		return ret;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 reg;
+
+		if (get_user(reg, uaddr))
+			return -EFAULT;
+
+		return vgic_attr_regs_access(dev, attr, &reg, true);
+	}
+
+	}
+
+	return -ENXIO;
+}
+
+static int vgic_get_common_attr(struct kvm_device *dev,
+				struct kvm_device_attr *attr)
 {
 	int r = -ENXIO;
 

@@ -2529,27 +2545,41 @@ static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 			return -EFAULT;
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+
+		r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
+		break;
+	}
+
+	}
+
+	return r;
+}
+
+static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int ret;
+
+	ret = vgic_get_common_attr(dev, attr);
+	if (ret != -ENXIO)
+		return ret;
 
+	switch (attr->group) {
 	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
 	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
 		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
 		u32 reg = 0;
 
-		r = vgic_attr_regs_access(dev, attr, &reg, false);
-		if (r)
-			return r;
-		r = put_user(reg, uaddr);
-		break;
-	}
-	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-		r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
-		break;
+		ret = vgic_attr_regs_access(dev, attr, &reg, false);
+		if (ret)
+			return ret;
+		return put_user(reg, uaddr);
 	}
 
 	}
 
-	return r;
+	return -ENXIO;
 }
 
 static int vgic_has_attr_regs(const struct mmio_range *ranges,

index a74b380..4735b9b 100644
@@ -75,33 +75,16 @@
  *   inactive as long as the external input line is held high.
  */
 
-#define VGIC_ADDR_UNDEF		(-1)
-#define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)
+#include "vgic.h"
 
-#define PRODUCT_ID_KVM		0x4b	/* ASCII code K */
-#define IMPLEMENTER_ARM		0x43b
 #define GICC_ARCH_VERSION_V2	0x2
 
-#define ACCESS_READ_VALUE	(1 << 0)
-#define ACCESS_READ_RAZ		(0 << 0)
-#define ACCESS_READ_MASK(x)	((x) & (1 << 0))
-#define ACCESS_WRITE_IGNORED	(0 << 1)
-#define ACCESS_WRITE_SETBIT	(1 << 1)
-#define ACCESS_WRITE_CLEARBIT	(2 << 1)
-#define ACCESS_WRITE_VALUE	(3 << 1)
-#define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
-
-static int vgic_init(struct kvm *kvm);
 static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
 static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
-static void vgic_update_state(struct kvm *kvm);
-static void vgic_kick_vcpus(struct kvm *kvm);
 static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi);
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
 static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
 static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
-static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 
 static const struct vgic_ops *vgic_ops;
 static const struct vgic_params *vgic;

@@ -175,8 +158,7 @@ static unsigned long *u64_to_bitmask(u64 *val)
 	return (unsigned long *)val;
 }
 
-static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
-				int cpuid, u32 offset)
+u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset)
 {
 	offset >>= 2;
 	if (!offset)

@@ -194,8 +176,8 @@ static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
 	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
 }
 
-static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
-				    int irq, int val)
+void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
+			     int irq, int val)
 {
 	unsigned long *reg;
 

@@ -217,7 +199,7 @@ static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
 	return x->private + cpuid;
 }
 
-static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
+unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
 {
 	return x->shared;
 }

@@ -244,7 +226,7 @@ static void vgic_free_bytemap(struct vgic_bytemap *b)
 	b->shared = NULL;
 }
 
-static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
+u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
 {
 	u32 *reg;
 

@@ -341,14 +323,14 @@ static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
 	return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
 }
 
-static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
+void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
 	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
 }
 
-static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
+void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 

@@ -364,7 +346,7 @@ static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
 			vcpu->arch.vgic_cpu.pending_shared);
 }
 
-static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
+void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
 {
 	if (irq < VGIC_NR_PRIVATE_IRQS)
 		clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);

@@ -378,16 +360,6 @@ static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
 	return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
 }
 
-static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
-{
-	return le32_to_cpu(*((u32 *)mmio->data)) & mask;
-}
-
-static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
-{
-	*((u32 *)mmio->data) = cpu_to_le32(value) & mask;
-}
-
 /**
  * vgic_reg_access - access vgic register
  * @mmio:   pointer to the data describing the mmio access

@@ -399,8 +371,8 @@ static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
  * modes defined for vgic register access
  * (read,raz,write-ignored,setbit,clearbit,write)
  */
-static void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
-			    phys_addr_t offset, int mode)
+void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
+		     phys_addr_t offset, int mode)
 {
 	int word_offset = (offset & 3) * 8;
 	u32 mask = (1UL << (mmio->len * 8)) - 1;

@@ -484,16 +456,16 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu,
-			       struct kvm_exit_mmio *mmio, phys_addr_t offset)
+bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
+			phys_addr_t offset)
 {
 	vgic_reg_access(mmio, NULL, offset,
 			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
 	return false;
 }
 
-static bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
-				   phys_addr_t offset, int vcpu_id, int access)
+bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
+			    phys_addr_t offset, int vcpu_id, int access)
 {
 	u32 *reg;
 	int mode = ACCESS_READ_VALUE | access;

@@ -530,9 +502,9 @@ static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
 				      vcpu->vcpu_id, ACCESS_WRITE_CLEARBIT);
 }
 
-static bool vgic_handle_set_pending_reg(struct kvm *kvm,
-					struct kvm_exit_mmio *mmio,
-					phys_addr_t offset, int vcpu_id)
+bool vgic_handle_set_pending_reg(struct kvm *kvm,
+				 struct kvm_exit_mmio *mmio,
+				 phys_addr_t offset, int vcpu_id)
 {
 	u32 *reg, orig;
 	u32 level_mask;

@@ -567,9 +539,9 @@ static bool vgic_handle_set_pending_reg(struct kvm *kvm,
 	return false;
 }
 
-static bool vgic_handle_clear_pending_reg(struct kvm *kvm,
-					  struct kvm_exit_mmio *mmio,
-					  phys_addr_t offset, int vcpu_id)
+bool vgic_handle_clear_pending_reg(struct kvm *kvm,
+				   struct kvm_exit_mmio *mmio,
+				   phys_addr_t offset, int vcpu_id)
 {
 	u32 *level_active;
 	u32 *reg, orig;

@@ -741,8 +713,8 @@ static u16 vgic_cfg_compress(u32 val)
  * LSB is always 0. As such, we only keep the upper bit, and use the
  * two above functions to compress/expand the bits
  */
-static bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
-				phys_addr_t offset)
+bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
+			 phys_addr_t offset)
 {
 	u32 val;
 

@@ -818,7 +790,7 @@ static void vgic_v2_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
  * to the distributor but the active state stays in the LRs, because we don't
  * track the active state on the distributor side.
  */
-static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
+void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	int i;

@@ -943,21 +915,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
 }
 
-/*
- * I would have liked to use the kvm_bus_io_*() API instead, but it
- * cannot cope with banked registers (only the VM pointer is passed
- * around, and we need the vcpu). One of these days, someone please
- * fix it!
- */
-struct mmio_range {
-	phys_addr_t base;
-	unsigned long len;
-	int bits_per_irq;
-	bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
-			    phys_addr_t offset);
-};
-
-static const struct mmio_range vgic_dist_ranges[] = {
+static const struct kvm_mmio_range vgic_dist_ranges[] = {
 	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,

@@ -1042,12 +1000,12 @@ static const struct mmio_range vgic_dist_ranges[] = {
 	{}
 };
 
-static const
-struct mmio_range *find_matching_range(const struct mmio_range *ranges,
+const
+struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges,
 				       struct kvm_exit_mmio *mmio,
 				       phys_addr_t offset)
 {
-	const struct mmio_range *r = ranges;
+	const struct kvm_mmio_range *r = ranges;
 
 	while (r->len) {
 		if (offset >= r->base &&

@@ -1060,7 +1018,7 @@ struct mmio_range *find_matching_range(const struct mmio_range *ranges,
 }
 
 static bool vgic_validate_access(const struct vgic_dist *dist,
-				 const struct mmio_range *range,
+				 const struct kvm_mmio_range *range,
 				 unsigned long offset)
 {
 	int irq;

@@ -1088,7 +1046,7 @@ static bool vgic_validate_access(const struct vgic_dist *dist,
 static bool call_range_handler(struct kvm_vcpu *vcpu,
 			       struct kvm_exit_mmio *mmio,
 			       unsigned long offset,
-			       const struct mmio_range *range)
+			       const struct kvm_mmio_range *range)
 {
 	u32 *data32 = (void *)mmio->data;
 	struct kvm_exit_mmio mmio32;

@@ -1132,18 +1090,18 @@ static bool call_range_handler(struct kvm_vcpu *vcpu,
  *
  * returns true if the MMIO access could be performed
  */
-static bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
+bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			    struct kvm_exit_mmio *mmio,
-			    const struct mmio_range *ranges,
+			    const struct kvm_mmio_range *ranges,
 			    unsigned long mmio_base)
 {
-	const struct mmio_range *range;
+	const struct kvm_mmio_range *range;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	bool updated_state;
 	unsigned long offset;
 
 	offset = mmio->phys_addr - mmio_base;
-	range = find_matching_range(ranges, mmio, offset);
+	range = vgic_find_range(ranges, mmio, offset);
 	if (unlikely(!range || !range->handle_mmio)) {
 		pr_warn("Unhandled access %d %08llx %d\n",
 			mmio->is_write, mmio->phys_addr, mmio->len);

@@ -1169,12 +1127,6 @@ static bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	return true;
 }
 
-static inline bool is_in_range(phys_addr_t addr, unsigned long len,
-			       phys_addr_t baseaddr, unsigned long size)
-{
-	return (addr >= baseaddr) && (addr + len <= baseaddr + size);
-}
-
 static bool vgic_v2_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 				struct kvm_exit_mmio *mmio)
 {

@@ -1301,7 +1253,7 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
  * Update the interrupt state and determine which CPUs have pending
  * interrupts. Must be called with distributor lock held.
  */
-static void vgic_update_state(struct kvm *kvm)
+void vgic_update_state(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;

@@ -1362,12 +1314,12 @@ static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
 	vgic_ops->disable_underflow(vcpu);
 }
 
-static inline void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
 {
 	vgic_ops->get_vmcr(vcpu, vmcr);
 }
 
-static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
 {
 	vgic_ops->set_vmcr(vcpu, vmcr);
 }

@@ -1417,7 +1369,7 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
  * Queue an interrupt to a CPU virtual interface. Return true on success,
  * or false if it wasn't possible to queue it.
  */
-static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
+bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

@@ -1703,7 +1655,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
-static void vgic_kick_vcpus(struct kvm *kvm)
+void vgic_kick_vcpus(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	int c;

@@ -1946,7 +1898,7 @@ static int vgic_v2_init_model(struct kvm *kvm)
  * Allocate and initialize the various data structures. Must be called
  * with kvm->lock held!
  */
-static int vgic_init(struct kvm *kvm)
+int vgic_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;

@@ -2086,7 +2038,7 @@ out:
 	return ret;
 }
 
-static int vgic_v2_init_emulation(struct kvm *kvm)
+int vgic_v2_init_emulation(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 

@@ -2327,7 +2279,7 @@ static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
  * CPU Interface Register accesses - these are not accessed by the VM, but by
  * user space for saving and restoring VGIC state.
  */
-static const struct mmio_range vgic_cpu_ranges[] = {
+static const struct kvm_mmio_range vgic_cpu_ranges[] = {
 	{
 		.base		= GIC_CPU_CTRL,
 		.len		= 12,

@@ -2354,7 +2306,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 				 struct kvm_device_attr *attr,
 				 u32 *reg, bool is_write)
 {
-	const struct mmio_range *r = NULL, *ranges;
+	const struct kvm_mmio_range *r = NULL, *ranges;
 	phys_addr_t offset;
 	int ret, cpuid, c;
 	struct kvm_vcpu *vcpu, *tmp_vcpu;

@@ -2395,7 +2347,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 	default:
 		BUG();
 	}
-	r = find_matching_range(ranges, &mmio, offset);
+	r = vgic_find_range(ranges, &mmio, offset);
 
 	if (unlikely(!r || !r->handle_mmio)) {
 		ret = -ENXIO;

@@ -2441,8 +2393,7 @@ out:
 	return ret;
 }
 
-static int vgic_set_common_attr(struct kvm_device *dev,
-				struct kvm_device_attr *attr)
+int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	int r;
 

@@ -2526,8 +2477,7 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return -ENXIO;
 }
 
-static int vgic_get_common_attr(struct kvm_device *dev,
-				struct kvm_device_attr *attr)
+int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	int r = -ENXIO;
 

@@ -2582,13 +2532,12 @@ static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return -ENXIO;
 }
 
-static int vgic_has_attr_regs(const struct mmio_range *ranges,
-			      phys_addr_t offset)
+int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset)
 {
 	struct kvm_exit_mmio dev_attr_mmio;
 
 	dev_attr_mmio.len = 4;
-	if (find_matching_range(ranges, &dev_attr_mmio, offset))
+	if (vgic_find_range(ranges, &dev_attr_mmio, offset))
 		return 0;
 	else
 		return -ENXIO;

@@ -2623,12 +2572,12 @@ static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return -ENXIO;
 }
 
-static void vgic_destroy(struct kvm_device *dev)
+void vgic_destroy(struct kvm_device *dev)
 {
 	kfree(dev);
 }
 
-static int vgic_create(struct kvm_device *dev, u32 type)
+int vgic_create(struct kvm_device *dev, u32 type)
 {
 	return kvm_vgic_create(dev->kvm, type);
 }

120 lines not on this page · raw message

849 lines not on this page · raw message

902 lines not on this page · raw message

index adcc0d7..3f83db2 100644
@@ -37,6 +37,7 @@ struct kvm_exit_mmio {
 	u8		data[8];
 	u32		len;
 	bool		is_write;
+	void		*private;
 };
 
 static inline void kvm_prepare_mmio(struct kvm_run *run,

index fc2f689..9f52beb 100644
@@ -40,6 +40,7 @@ struct kvm_exit_mmio {
 	u8		data[8];
 	u32		len;
 	bool		is_write;
+	void		*private;
 };
 
 static inline void kvm_prepare_mmio(struct kvm_run *run,

index 750d956..53160f1 100644
@@ -711,6 +711,7 @@ static bool call_range_handler(struct kvm_vcpu *vcpu,
 
 	mmio32.len = 4;
 	mmio32.is_write = mmio->is_write;
+	mmio32.private = mmio->private;
 
 	mmio32.phys_addr = mmio->phys_addr + 4;
 	if (mmio->is_write)

index ff04afd..98c3016 100644
@@ -162,7 +162,11 @@ struct vgic_dist {
 
 	/* Distributor and vcpu interface mapping in the guest */
 	phys_addr_t		vgic_dist_base;
-	phys_addr_t		vgic_cpu_base;
+	/* GICv2 and GICv3 use different mapped register blocks */
+	union {
+		phys_addr_t		vgic_cpu_base;
+		phys_addr_t		vgic_redist_base;
+	};
 
 	/* Distributor enabled */
 	u32			enabled;

@@ -224,6 +228,9 @@ struct vgic_dist {
 	 */
 	struct vgic_bitmap	*irq_spi_target;
 
+	/* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */
+	u32			*irq_spi_mpidr;
+
 	/* Bitmap indicating which CPU has something pending */
 	unsigned long		*irq_pending_on_cpu;
 

index 1e8b0cf..3fb4d85 100644
@@ -33,6 +33,7 @@
 #define GICD_SETSPI_SR			0x0050
 #define GICD_CLRSPI_SR			0x0058
 #define GICD_SEIR			0x0068
+#define GICD_IGROUPR			0x0080
 #define GICD_ISENABLER			0x0100
 #define GICD_ICENABLER			0x0180
 #define GICD_ISPENDR			0x0200

@@ -41,14 +42,37 @@
 #define GICD_ICACTIVER			0x0380
 #define GICD_IPRIORITYR			0x0400
 #define GICD_ICFGR			0x0C00
+#define GICD_IGRPMODR			0x0D00
+#define GICD_NSACR			0x0E00
 #define GICD_IROUTER			0x6000
+#define GICD_IDREGS			0xFFD0
 #define GICD_PIDR2			0xFFE8
 
+/*
+ * Those registers are actually from GICv2, but the spec demands that they
+ * are implemented as RES0 if ARE is 1 (which we do in KVM's emulated GICv3).
+ */
+#define GICD_ITARGETSR			0x0800
+#define GICD_SGIR			0x0F00
+#define GICD_CPENDSGIR			0x0F10
+#define GICD_SPENDSGIR			0x0F20
+
 #define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_DS			(1U << 6)
 #define GICD_CTLR_ARE_NS		(1U << 4)
 #define GICD_CTLR_ENABLE_G1A		(1U << 1)
 #define GICD_CTLR_ENABLE_G1		(1U << 0)
 
+/*
+ * In systems with a single security state (what we emulate in KVM)
+ * the meaning of the interrupt group enable bits is slightly different
+ */
+#define GICD_CTLR_ENABLE_SS_G1		(1U << 1)
+#define GICD_CTLR_ENABLE_SS_G0		(1U << 0)
+
+#define GICD_TYPER_LPIS			(1U << 17)
+#define GICD_TYPER_MBIS			(1U << 16)
+
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 #define GICD_TYPER_LPIS			(1U << 17)

@@ -60,6 +84,8 @@
 #define GIC_PIDR2_ARCH_GICv3		0x30
 #define GIC_PIDR2_ARCH_GICv4		0x40
 
+#define GIC_V3_DIST_SIZE		0x10000
+
 /*
  * Re-Distributor registers, offsets from RD_base
  */

@@ -78,6 +104,7 @@
 #define GICR_SYNCR			0x00C0
 #define GICR_MOVLPIR			0x0100
 #define GICR_MOVALLR			0x0110
+#define GICR_IDREGS			GICD_IDREGS
 #define GICR_PIDR2			GICD_PIDR2
 
 #define GICR_CTLR_ENABLE_LPIS		(1UL << 0)

@@ -104,6 +131,7 @@
 /*
  * Re-Distributor registers, offsets from SGI_base
  */
+#define GICR_IGROUPR0			GICD_IGROUPR
 #define GICR_ISENABLER0			GICD_ISENABLER
 #define GICR_ICENABLER0			GICD_ICENABLER
 #define GICR_ISPENDR0			GICD_ISPENDR

@@ -112,11 +140,15 @@
 #define GICR_ICACTIVER0			GICD_ICACTIVER
 #define GICR_IPRIORITYR0		GICD_IPRIORITYR
 #define GICR_ICFGR0			GICD_ICFGR
+#define GICR_IGRPMODR0			GICD_IGRPMODR
+#define GICR_NSACR			GICD_NSACR
 
 #define GICR_TYPER_PLPIS		(1U << 0)
 #define GICR_TYPER_VLPIS		(1U << 1)
 #define GICR_TYPER_LAST			(1U << 4)
 
+#define GIC_V3_REDIST_SIZE		0x20000
+
 #define LPI_PROP_GROUP1			(1 << 1)
 #define LPI_PROP_ENABLED		(1 << 0)
 

index 703eeed..83d770e 100644
@@ -1043,6 +1043,7 @@ void kvm_unregister_device_ops(u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
+extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 

index a37fd12..b4e6f1e 100644
@@ -952,6 +952,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
 	KVM_DEV_TYPE_FLIC,
 #define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_ARM_VGIC_V3,
+#define KVM_DEV_TYPE_ARM_VGIC_V3	KVM_DEV_TYPE_ARM_VGIC_V3
 	KVM_DEV_TYPE_MAX,
 };
 

924 lines not on this page · raw message

index 53160f1..e0a23da 100644
@@ -1251,7 +1251,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 	struct kvm_vcpu *vcpu;
 	int edge_triggered, level_triggered;
 	int enabled;
-	bool ret = true;
+	bool ret = true, can_inject = true;
 
 	spin_lock(&dist->lock);
 

@@ -1266,6 +1266,11 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 
 	if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
 		cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
+		if (cpuid == VCPU_NOT_ALLOCATED) {
+			/* Pretend we use CPU0, and prevent injection */
+			cpuid = 0;
+			can_inject = false;
+		}
 		vcpu = kvm_get_vcpu(kvm, cpuid);
 	}
 

@@ -1288,7 +1293,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 
 	enabled = vgic_irq_is_enabled(vcpu, irq_num);
 
-	if (!enabled) {
+	if (!enabled || !can_inject) {
 		ret = false;
 		goto out;
 	}

@@ -1431,6 +1436,7 @@ void kvm_vgic_destroy(struct kvm *kvm)
 	}
 	kfree(dist->irq_sgi_sources);
 	kfree(dist->irq_spi_cpu);
+	kfree(dist->irq_spi_mpidr);
 	kfree(dist->irq_spi_target);
 	kfree(dist->irq_pending_on_cpu);
 	dist->irq_sgi_sources = NULL;

@@ -1595,6 +1601,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+	kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
 
 out_unlock:
 	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {

index 96415a9..7a900b0 100644
@@ -35,6 +35,8 @@
 #define ACCESS_WRITE_VALUE	(3 << 1)
 #define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
 
+#define VCPU_NOT_ALLOCATED	((u8)-1)
+
 unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x);
 
 void vgic_update_state(struct kvm *kvm);

@@ -116,5 +118,6 @@ int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
 
 int vgic_init(struct kvm *kvm);
 int vgic_v2_init_emulation(struct kvm *kvm);
+int vgic_v3_init_emulation(struct kvm *kvm);
 
 #endif