[PATCH RFC v3 21/27] KVM: arm64: Support Z and P registers in streaming mode

[Mark Brown <broonie@kernel.org>]

SME introduces a mode called streaming mode where the Z, P and optionally
FFR registers can be accessed using the SVE instructions but with the SME
vector length. Reflect this in the ABI for accessing the guest registers by
making the vector length for the vcpu reflect the vector length that would
be seen by the guest were it running, using the SME vector length when the
guest is configured for streaming mode.

Since SME may be present without SVE we also update the existing checks for
access to the Z, P and V registers to check for either SVE or streaming
mode. When not in streaming mode the guest floating point state may be
accessed via the V registers.

Any VMM that supports SME must be aware of the need to configure streaming
mode prior to writing the floating point registers that this creates.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  9 +++++++--
 arch/arm64/kvm/guest.c            | 38 ++++++++++++++++++++++++++++++++++----
 2 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f72024ffc89d955b3a0a20b6503ceb451abe824f..7393672fa0ee9c4ac13adb48a973f94929f767ea 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1017,16 +1017,18 @@ struct kvm_vcpu_arch {
 	size_t __size_ret;						\
 	unsigned int __vcpu_vq;						\
 									\
-	if (WARN_ON(!sve_vl_valid((vcpu)->arch.max_vl[ARM64_VEC_SVE]))) { \
+	if (WARN_ON(!sve_vl_valid(vcpu_max_vl(vcpu)))) {		\
 		__size_ret = 0;						\
 	} else {							\
-		__vcpu_vq = vcpu_sve_max_vq(vcpu);			\
+		__vcpu_vq = sve_vl_from_vq(vcpu_max_vl(vcpu));		\
 		__size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq);		\
 	}								\
 									\
 	__size_ret;							\
 })
 
+#define vcpu_sme_state(vcpu) (kern_hyp_va((vcpu)->arch.sme_state))
+
 /*
  * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
  * memory backed version of a register, and not the one most recently
@@ -1583,4 +1585,7 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(system_supports_sme() &&			\
 	 kvm_has_feat((k), ID_AA64PFR1_EL1, SME, SME2))
 
+#define vcpu_in_streaming_mode(vcpu) \
+	(__vcpu_sys_reg(vcpu, SVCR) & SVCR_SM_MASK)
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 8820cd42a27ac05874ed52c572c1dd9b29a77a1b..cf468ac93c9e75d642d7293e020d04c4267ffff4 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -73,6 +73,11 @@ static u64 core_reg_offset_from_id(u64 id)
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
 }
 
+static bool vcpu_has_sve_regs(const struct kvm_vcpu *vcpu)
+{
+	return vcpu_has_sve(vcpu) || vcpu_in_streaming_mode(vcpu);
+}
+
 static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 {
 	int size;
@@ -110,9 +115,10 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 	/*
 	 * The KVM_REG_ARM64_SVE regs must be used instead of
 	 * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on
-	 * SVE-enabled vcpus:
+	 * SVE-enabled vcpus or when a SME enabled vcpu is in
+	 * streaming mode:
 	 */
-	if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off))
+	if (vcpu_has_sve_regs(vcpu) && core_reg_offset_is_vreg(off))
 		return -EINVAL;
 
 	return size;
@@ -426,6 +432,24 @@ struct vec_state_reg_region {
 	unsigned int upad;	/* extra trailing padding in user memory */
 };
 
+/*
+ * We represent the Z and P registers to userspace using either the
+ * SVE or SME vector length, depending on which features the guest has
+ * and if the guest is in streaming mode.
+ */
+static unsigned int vcpu_sve_cur_vq(struct kvm_vcpu *vcpu)
+{
+	unsigned int vq = 0;
+
+	if (vcpu_has_sve(vcpu))
+		vq = vcpu_sve_max_vq(vcpu);
+
+	if (vcpu_in_streaming_mode(vcpu))
+		vq = vcpu_sme_max_vq(vcpu);
+
+	return vq;
+}
+
 /*
  * Validate SVE register ID and get sanitised bounds for user/kernel SVE
  * register copy
@@ -466,7 +490,7 @@ static int sve_reg_to_region(struct vec_state_reg_region *region,
 		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
 			return -ENOENT;
 
-		vq = vcpu_sve_max_vq(vcpu);
+		vq = vcpu_sve_cur_vq(vcpu);
 
 		reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) -
 				SVE_SIG_REGS_OFFSET;
@@ -476,7 +500,7 @@ static int sve_reg_to_region(struct vec_state_reg_region *region,
 		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
 			return -ENOENT;
 
-		vq = vcpu_sve_max_vq(vcpu);
+		vq = vcpu_sve_cur_vq(vcpu);
 
 		reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) -
 				SVE_SIG_REGS_OFFSET;
@@ -515,6 +539,9 @@ static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!kvm_arm_vcpu_vec_finalized(vcpu))
 		return -EPERM;
 
+	if (!vcpu_has_sve_regs(vcpu))
+		return -EBUSY;
+
 	if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset,
 			 region.klen) ||
 	    clear_user(uptr + region.klen, region.upad))
@@ -541,6 +568,9 @@ static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!kvm_arm_vcpu_vec_finalized(vcpu))
 		return -EPERM;
 
+	if (!vcpu_has_sve_regs(vcpu))
+		return -EBUSY;
+
 	if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr,
 			   region.klen))
 		return -EFAULT;

-- 
2.39.5