KVM: arm/arm64: vgic: Add distributor and redistributor access

VGICv3 Distributor and Redistributor registers are accessed using
KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
with KVM_SET_DEVICE_ATTR and KVM_GET_DEVICE_ATTR ioctls.
These registers are accessed as 32-bit and cpu mpidr
value passed along with register offset is used to identify the
cpu for redistributor registers access.

The version of VGIC v3 specification is defined here
Documentation/virtual/kvm/devices/arm-vgic-v3.txt

Also update arch/arm/include/uapi/asm/kvm.h to compile for
AArch32 mode.
Signed-off-by: NVijaya Kumar K <Vijaya.Kumar@cavium.com>
Reviewed-by: NChristoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: NEric Auger <eric.auger@redhat.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

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

@@ -181,10 +181,14 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
 #define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+			(0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 #define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
 
 /* KVM_IRQ_LINE irq field index values */

arch/arm64/include/uapi/asm/kvm.h

@@ -201,10 +201,14 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
 #define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+			(0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 #define KVM_DEV_ARM_VGIC_GRP_CTRL	4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
 
 /* Device Control API on vcpu fd */

virt/kvm/arm/vgic/vgic-kvm-device.c

@@ -17,6 +17,7 @@
 #include <kvm/arm_vgic.h>
 #include <linux/uaccess.h>
 #include <asm/kvm_mmu.h>
+#include <asm/cputype.h>
 #include "vgic.h"
 
 /* common helpers */
@@ -230,14 +231,8 @@ int kvm_register_vgic_device(unsigned long type)
 	return ret;
 }
 
-struct vgic_reg_attr {
-	struct kvm_vcpu *vcpu;
-	gpa_t addr;
-};
-
-static int parse_vgic_v2_attr(struct kvm_device *dev,
-			      struct kvm_device_attr *attr,
-			      struct vgic_reg_attr *reg_attr)
+int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
+		       struct vgic_reg_attr *reg_attr)
 {
 	int cpuid;
 
@@ -292,14 +287,14 @@ static bool lock_all_vcpus(struct kvm *kvm)
 }
 
 /**
- * vgic_attr_regs_access_v2 - allows user space to access VGIC v2 state
+ * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state
  *
  * @dev:      kvm device handle
  * @attr:     kvm device attribute
  * @reg:      address the value is read or written
  * @is_write: true if userspace is writing a register
  */
-static int vgic_attr_regs_access_v2(struct kvm_device *dev,
+static int vgic_v2_attr_regs_access(struct kvm_device *dev,
 				    struct kvm_device_attr *attr,
 				    u32 *reg, bool is_write)
 {
@@ -308,7 +303,7 @@ static int vgic_attr_regs_access_v2(struct kvm_device *dev,
 	struct kvm_vcpu *vcpu;
 	int ret;
 
-	ret = parse_vgic_v2_attr(dev, attr, &reg_attr);
+	ret = vgic_v2_parse_attr(dev, attr, &reg_attr);
 	if (ret)
 		return ret;
 
@@ -362,7 +357,7 @@ static int vgic_v2_set_attr(struct kvm_device *dev,
 		if (get_user(reg, uaddr))
 			return -EFAULT;
 
-		return vgic_attr_regs_access_v2(dev, attr, &reg, true);
+		return vgic_v2_attr_regs_access(dev, attr, &reg, true);
 	}
 	}
 
@@ -384,7 +379,7 @@ static int vgic_v2_get_attr(struct kvm_device *dev,
 		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
 		u32 reg = 0;
 
-		ret = vgic_attr_regs_access_v2(dev, attr, &reg, false);
+		ret = vgic_v2_attr_regs_access(dev, attr, &reg, false);
 		if (ret)
 			return ret;
 		return put_user(reg, uaddr);
@@ -428,16 +423,149 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.has_attr = vgic_v2_has_attr,
 };
 
+int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
+		       struct vgic_reg_attr *reg_attr)
+{
+	unsigned long vgic_mpidr, mpidr_reg;
+
+	/*
+	 * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group,
+	 * attr might not hold MPIDR. Hence assume vcpu0.
+	 */
+	if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) {
+		vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >>
+			      KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT;
+
+		mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr);
+		reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg);
+	} else {
+		reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0);
+	}
+
+	if (!reg_attr->vcpu)
+		return -EINVAL;
+
+	reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+
+	return 0;
+}
+
+/*
+ * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state
+ *
+ * @dev:      kvm device handle
+ * @attr:     kvm device attribute
+ * @reg:      address the value is read or written
+ * @is_write: true if userspace is writing a register
+ */
+static int vgic_v3_attr_regs_access(struct kvm_device *dev,
+				    struct kvm_device_attr *attr,
+				    u64 *reg, bool is_write)
+{
+	struct vgic_reg_attr reg_attr;
+	gpa_t addr;
+	struct kvm_vcpu *vcpu;
+	int ret;
+	u32 tmp32;
+
+	ret = vgic_v3_parse_attr(dev, attr, &reg_attr);
+	if (ret)
+		return ret;
+
+	vcpu = reg_attr.vcpu;
+	addr = reg_attr.addr;
+
+	mutex_lock(&dev->kvm->lock);
+
+	if (unlikely(!vgic_initialized(dev->kvm))) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (!lock_all_vcpus(dev->kvm)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+		if (is_write)
+			tmp32 = *reg;
+
+		ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &tmp32);
+		if (!is_write)
+			*reg = tmp32;
+		break;
+	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
+		if (is_write)
+			tmp32 = *reg;
+
+		ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &tmp32);
+		if (!is_write)
+			*reg = tmp32;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	unlock_all_vcpus(dev->kvm);
+out:
+	mutex_unlock(&dev->kvm->lock);
+	return ret;
+}
+
 static int vgic_v3_set_attr(struct kvm_device *dev,
 			    struct kvm_device_attr *attr)
 {
-	return vgic_set_common_attr(dev, 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_REDIST_REGS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 tmp32;
+		u64 reg;
+
+		if (get_user(tmp32, uaddr))
+			return -EFAULT;
+
+		reg = tmp32;
+		return vgic_v3_attr_regs_access(dev, attr, &reg, true);
+	}
+	}
+	return -ENXIO;
 }
 
 static int vgic_v3_get_attr(struct kvm_device *dev,
 			    struct kvm_device_attr *attr)
 {
-	return vgic_get_common_attr(dev, 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_REDIST_REGS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u64 reg;
+		u32 tmp32;
+
+		ret = vgic_v3_attr_regs_access(dev, attr, &reg, false);
+		if (ret)
+			return ret;
+		tmp32 = reg;
+		return put_user(tmp32, uaddr);
+	}
+	}
+
+	return -ENXIO;
 }
 
 static int vgic_v3_has_attr(struct kvm_device *dev,
@@ -451,6 +579,9 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
 			return 0;
 		}
 		break;
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
+		return vgic_v3_has_attr_regs(dev, attr);
 	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
 		return 0;
 	case KVM_DEV_ARM_VGIC_GRP_CTRL:

virt/kvm/arm/vgic/vgic-mmio-v2.c

@@ -369,21 +369,30 @@ unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev)
 
 int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
-	int nr_irqs = dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
-	const struct vgic_register_region *regions;
+	const struct vgic_register_region *region;
+	struct vgic_io_device iodev;
+	struct vgic_reg_attr reg_attr;
+	struct kvm_vcpu *vcpu;
 	gpa_t addr;
-	int nr_regions, i, len;
+	int ret;
+
+	ret = vgic_v2_parse_attr(dev, attr, &reg_attr);
+	if (ret)
+		return ret;
 
-	addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+	vcpu = reg_attr.vcpu;
+	addr = reg_attr.addr;
 
 	switch (attr->group) {
 	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-		regions = vgic_v2_dist_registers;
-		nr_regions = ARRAY_SIZE(vgic_v2_dist_registers);
+		iodev.regions = vgic_v2_dist_registers;
+		iodev.nr_regions = ARRAY_SIZE(vgic_v2_dist_registers);
+		iodev.base_addr = 0;
 		break;
 	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		regions = vgic_v2_cpu_registers;
-		nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers);
+		iodev.regions = vgic_v2_cpu_registers;
+		iodev.nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers);
+		iodev.base_addr = 0;
 		break;
 	default:
 		return -ENXIO;
@@ -393,18 +402,11 @@ int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
 	if (addr & 3)
 		return -ENXIO;
 
-	for (i = 0; i < nr_regions; i++) {
-		if (regions[i].bits_per_irq)
-			len = (regions[i].bits_per_irq * nr_irqs) / 8;
-		else
-			len = regions[i].len;
-
-		if (regions[i].reg_offset <= addr &&
-		    regions[i].reg_offset + len > addr)
-			return 0;
-	}
+	region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32));
+	if (!region)
+		return -ENXIO;
 
-	return -ENXIO;
+	return 0;
 }
 
 int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write,

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -18,6 +18,8 @@
 #include <kvm/arm_vgic.h>
 
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
 
 #include "vgic.h"
 #include "vgic-mmio.h"
@@ -433,6 +435,9 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICD_CTLR,
 		vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc, 16,
 		VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICD_STATUSR,
+		vgic_mmio_read_rao, vgic_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR,
 		vgic_mmio_read_rao, vgic_mmio_write_wi, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
@@ -480,12 +485,18 @@ static const struct vgic_register_region vgic_v3_rdbase_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICR_CTLR,
 		vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4,
 		VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_STATUSR,
+		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
 		vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_TYPER,
 		vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_WAKER,
+		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER,
 		vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
@@ -606,6 +617,48 @@ int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
 	return ret;
 }
 
+int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	const struct vgic_register_region *region;
+	struct vgic_io_device iodev;
+	struct vgic_reg_attr reg_attr;
+	struct kvm_vcpu *vcpu;
+	gpa_t addr;
+	int ret;
+
+	ret = vgic_v3_parse_attr(dev, attr, &reg_attr);
+	if (ret)
+		return ret;
+
+	vcpu = reg_attr.vcpu;
+	addr = reg_attr.addr;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+		iodev.regions = vgic_v3_dist_registers;
+		iodev.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers);
+		iodev.base_addr = 0;
+		break;
+	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{
+		iodev.regions = vgic_v3_rdbase_registers;
+		iodev.nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
+		iodev.base_addr = 0;
+		break;
+	}
+	default:
+		return -ENXIO;
+	}
+
+	/* We only support aligned 32-bit accesses. */
+	if (addr & 3)
+		return -ENXIO;
+
+	region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32));
+	if (!region)
+		return -ENXIO;
+
+	return 0;
+}
 /*
  * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI
  * generation register ICC_SGI1R_EL1) with a given VCPU.
@@ -712,3 +765,35 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
+
+int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+			 int offset, u32 *val)
+{
+	struct vgic_io_device dev = {
+		.regions = vgic_v3_dist_registers,
+		.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers),
+	};
+
+	return vgic_uaccess(vcpu, &dev, is_write, offset, val);
+}
+
+int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+			   int offset, u32 *val)
+{
+	struct vgic_io_device rd_dev = {
+		.regions = vgic_v3_rdbase_registers,
+		.nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers),
+	};
+
+	struct vgic_io_device sgi_dev = {
+		.regions = vgic_v3_sgibase_registers,
+		.nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers),
+	};
+
+	/* SGI_base is the next 64K frame after RD_base */
+	if (offset >= SZ_64K)
+		return vgic_uaccess(vcpu, &sgi_dev, is_write, offset - SZ_64K,
+				    val);
+	else
+		return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val);
+}

virt/kvm/arm/vgic/vgic-mmio.c

@@ -475,7 +475,7 @@ static bool check_region(const struct kvm *kvm,
 	return false;
 }
 
-static const struct vgic_register_region *
+const struct vgic_register_region *
 vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
 		     gpa_t addr, int len)
 {

virt/kvm/arm/vgic/vgic.h

@@ -30,6 +30,28 @@
 
 #define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS)
 
+#define VGIC_AFFINITY_0_SHIFT 0
+#define VGIC_AFFINITY_0_MASK (0xffUL << VGIC_AFFINITY_0_SHIFT)
+#define VGIC_AFFINITY_1_SHIFT 8
+#define VGIC_AFFINITY_1_MASK (0xffUL << VGIC_AFFINITY_1_SHIFT)
+#define VGIC_AFFINITY_2_SHIFT 16
+#define VGIC_AFFINITY_2_MASK (0xffUL << VGIC_AFFINITY_2_SHIFT)
+#define VGIC_AFFINITY_3_SHIFT 24
+#define VGIC_AFFINITY_3_MASK (0xffUL << VGIC_AFFINITY_3_SHIFT)
+
+#define VGIC_AFFINITY_LEVEL(reg, level) \
+	((((reg) & VGIC_AFFINITY_## level ##_MASK) \
+	>> VGIC_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level))
+
+/*
+ * The Userspace encodes the affinity differently from the MPIDR,
+ * Below macro converts vgic userspace format to MPIDR reg format.
+ */
+#define VGIC_TO_MPIDR(val) (VGIC_AFFINITY_LEVEL(val, 0) | \
+			    VGIC_AFFINITY_LEVEL(val, 1) | \
+			    VGIC_AFFINITY_LEVEL(val, 2) | \
+			    VGIC_AFFINITY_LEVEL(val, 3))
+
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
 	if (irq->config == VGIC_CONFIG_EDGE)
@@ -45,6 +67,18 @@ struct vgic_vmcr {
 	u32	pmr;
 };
 
+struct vgic_reg_attr {
+	struct kvm_vcpu *vcpu;
+	gpa_t addr;
+};
+
+int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
+		       struct vgic_reg_attr *reg_attr);
+int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
+		       struct vgic_reg_attr *reg_attr);
+const struct vgic_register_region *
+vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
+		     gpa_t addr, int len);
 struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			      u32 intid);
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
@@ -97,7 +131,11 @@ bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
 int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
-
+int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
+int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+			 int offset, u32 *val);
+int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
+			 int offset, u32 *val);
 int kvm_register_vgic_device(unsigned long type);
 int vgic_lazy_init(struct kvm *kvm);
 int vgic_init(struct kvm *kvm);