KVM: arm64/sve: Add pseudo-register for the guest's vector lengths

This patch adds a new pseudo-register KVM_REG_ARM64_SVE_VLS to
allow userspace to set and query the set of vector lengths visible
to the guest.

In the future, multiple register slices per SVE register may be
visible through the ioctl interface.  Once the set of slices has
been determined we would not be able to allow the vector length set
to be changed any more, in order to avoid userspace seeing
inconsistent sets of registers.  For this reason, this patch adds
support for explicit finalization of the SVE configuration via the
KVM_ARM_VCPU_FINALIZE ioctl.

Finalization is the proper place to allocate the SVE register state
storage in vcpu->arch.sve_state, so this patch adds that as
appropriate.  The data is freed via kvm_arch_vcpu_uninit(), which
was previously a no-op on arm64.

To simplify the logic for determining what vector lengths can be
supported, some code is added to KVM init to work this out, in the
kvm_arm_init_arch_resources() hook.

The KVM_REG_ARM64_SVE_VLS pseudo-register is not exposed yet.
Subsequent patches will allow SVE to be turned on for guest vcpus,
making it visible.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Tested-by: zhang.lei <zhang.lei@jp.fujitsu.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

1 files changed, 111 insertions, 3 deletions

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 2aa80a59e2a2..086ab0508d69 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -206,6 +206,73 @@ out:
 	return err;
 }
 
+#define vq_word(vq) (((vq) - SVE_VQ_MIN) / 64)
+#define vq_mask(vq) ((u64)1 << ((vq) - SVE_VQ_MIN) % 64)
+
+static bool vq_present(
+	const u64 (*const vqs)[DIV_ROUND_UP(SVE_VQ_MAX - SVE_VQ_MIN + 1, 64)],
+	unsigned int vq)
+{
+	return (*vqs)[vq_word(vq)] & vq_mask(vq);
+}
+
+static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	unsigned int max_vq, vq;
+	u64 vqs[DIV_ROUND_UP(SVE_VQ_MAX - SVE_VQ_MIN + 1, 64)];
+
+	if (WARN_ON(!sve_vl_valid(vcpu->arch.sve_max_vl)))
+		return -EINVAL;
+
+	memset(vqs, 0, sizeof(vqs));
+
+	max_vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+	for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq)
+		if (sve_vq_available(vq))
+			vqs[vq_word(vq)] |= vq_mask(vq);
+
+	if (copy_to_user((void __user *)reg->addr, vqs, sizeof(vqs)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	unsigned int max_vq, vq;
+	u64 vqs[DIV_ROUND_UP(SVE_VQ_MAX - SVE_VQ_MIN + 1, 64)];
+
+	if (kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM; /* too late! */
+
+	if (WARN_ON(vcpu->arch.sve_state))
+		return -EINVAL;
+
+	if (copy_from_user(vqs, (const void __user *)reg->addr, sizeof(vqs)))
+		return -EFAULT;
+
+	max_vq = 0;
+	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; ++vq)
+		if (vq_present(&vqs, vq))
+			max_vq = vq;
+
+	if (max_vq > sve_vq_from_vl(kvm_sve_max_vl))
+		return -EINVAL;
+
+	for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq)
+		if (vq_present(&vqs, vq) != sve_vq_available(vq))
+			return -EINVAL;
+
+	/* Can't run with no vector lengths at all: */
+	if (max_vq < SVE_VQ_MIN)
+		return -EINVAL;
+
+	/* vcpu->arch.sve_state will be alloc'd by kvm_vcpu_finalize_sve() */
+	vcpu->arch.sve_max_vl = sve_vl_from_vq(max_vq);
+
+	return 0;
+}
+
 #define SVE_REG_SLICE_SHIFT	0
 #define SVE_REG_SLICE_BITS	5
 #define SVE_REG_ID_SHIFT	(SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS)
@@ -296,7 +363,19 @@ static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	struct sve_state_reg_region region;
 	char __user *uptr = (char __user *)reg->addr;
 
-	if (!vcpu_has_sve(vcpu) || sve_reg_to_region(&region, vcpu, reg))
+	if (!vcpu_has_sve(vcpu))
+		return -ENOENT;
+
+	/* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */
+	if (reg->id == KVM_REG_ARM64_SVE_VLS)
+		return get_sve_vls(vcpu, reg);
+
+	/* Otherwise, reg is an architectural SVE register... */
+
+	if (!kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM;
+
+	if (sve_reg_to_region(&region, vcpu, reg))
 		return -ENOENT;
 
 	if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset,
@@ -312,7 +391,19 @@ static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	struct sve_state_reg_region region;
 	const char __user *uptr = (const char __user *)reg->addr;
 
-	if (!vcpu_has_sve(vcpu) || sve_reg_to_region(&region, vcpu, reg))
+	if (!vcpu_has_sve(vcpu))
+		return -ENOENT;
+
+	/* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */
+	if (reg->id == KVM_REG_ARM64_SVE_VLS)
+		return set_sve_vls(vcpu, reg);
+
+	/* Otherwise, reg is an architectural SVE register... */
+
+	if (!kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM;
+
+	if (sve_reg_to_region(&region, vcpu, reg))
 		return -ENOENT;
 
 	if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr,
@@ -426,7 +517,11 @@ static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu)
 	if (!vcpu_has_sve(vcpu))
 		return 0;
 
-	return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */);
+	/* Policed by KVM_GET_REG_LIST: */
+	WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu));
+
+	return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */)
+		+ 1; /* KVM_REG_ARM64_SVE_VLS */
 }
 
 static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu,
@@ -441,6 +536,19 @@ static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu,
 	if (!vcpu_has_sve(vcpu))
 		return 0;
 
+	/* Policed by KVM_GET_REG_LIST: */
+	WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu));
+
+	/*
+	 * Enumerate this first, so that userspace can save/restore in
+	 * the order reported by KVM_GET_REG_LIST:
+	 */
+	reg = KVM_REG_ARM64_SVE_VLS;
+	if (put_user(reg, uindices++))
+		return -EFAULT;
+
+	++num_regs;
+
 	for (i = 0; i < slices; i++) {
 		for (n = 0; n < SVE_NUM_ZREGS; n++) {
 			reg = KVM_REG_ARM64_SVE_ZREG(n, i);