[PATCH RFC v2 18/22] KVM: arm64: Expose ZA to userspace

From: Mark Brown <broonie@kernel.org>
To: Marc Zyngier <maz@kernel.org>,
	Oliver Upton <oliver.upton@linux.dev>,
	 James Morse <james.morse@arm.com>,
	 Suzuki K Poulose <suzuki.poulose@arm.com>,
	 Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	 Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>,  Shuah Khan <shuah@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev,
	 linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	 linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
	 Mark Brown <broonie@kernel.org>
Subject: [PATCH RFC v2 18/22] KVM: arm64: Expose ZA to userspace
Date: Fri, 22 Dec 2023 16:21:26 +0000	[thread overview]
Message-ID: <20231222-kvm-arm64-sme-v2-18-da226cb180bb@kernel.org> (raw)
In-Reply-To: <20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.org>

The SME ZA matrix is a single SVL*SVL register which is available when
PSTATE.ZA is set. We follow the pattern established by the architecture
itself and expose this to userspace as a series of horizontal SVE vectors
with the streaming mode vector length, using the format already established
for the SVE vectors themselves.

For the purposes of exporting to userspace we ignore the value of
PSTATE.ZA, if PSTATE.ZA is clear when the guest is run then the guest will
need to set it to access ZA which would cause the value to be cleared. If
userspace reads ZA when PSTATE.ZA is clear then it will read whatever stale
data was last saved. This removes ordering requirements from userspace,
minimising the need to special case.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 14 ++++++
 arch/arm64/include/uapi/asm/kvm.h | 15 +++++++
 arch/arm64/kvm/guest.c            | 95 ++++++++++++++++++++++++++++++++++++++-
 3 files changed, 122 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a5ed0433edc6..a1aa9471084d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -846,6 +846,20 @@ void vcpu_fp_guest_to_user(struct kvm_vcpu *vcpu);
 	__size_ret;							\
 })
 
+#define vcpu_sme_state_size(vcpu) ({					\
+	size_t __size_ret;						\
+	unsigned int __vcpu_vq;						\
+									\
+	if (WARN_ON(!sve_vl_valid((vcpu)->arch.max_vl[ARM64_VEC_SME]))) { \
+		__size_ret = 0;						\
+	} else {							\
+		__vcpu_vq = vcpu_sme_max_vq(vcpu);			\
+		__size_ret = ZA_SIG_REGS_SIZE(__vcpu_vq);		\
+	}								\
+									\
+	__size_ret;							\
+})
+
 /*
  * 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
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 02642bb96496..00fb2ea4c057 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -356,6 +356,21 @@ struct kvm_arm_counter_offset {
 /* SME registers */
 #define KVM_REG_ARM64_SME		(0x17 << KVM_REG_ARM_COPROC_SHIFT)
 
+#define KVM_ARM64_SME_VQ_MIN __SVE_VQ_MIN
+#define KVM_ARM64_SME_VQ_MAX __SVE_VQ_MAX
+
+/* ZA and ZTn occupy blocks at the following offsets within this range: */
+#define KVM_REG_ARM64_SME_ZA_BASE	0
+#define KVM_REG_ARM64_SME_ZT_BASE	0x600
+
+#define KVM_ARM64_SME_MAX_ZAHREG	(__SVE_VQ_BYTES * KVM_ARM64_SME_VQ_MAX)
+
+#define KVM_REG_ARM64_SME_ZAHREG(n, i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SME | KVM_REG_ARM64_SME_ZA_BASE | \
+	 KVM_REG_SIZE_U2048 |						\
+	 (((n) & (KVM_ARM64_SME_MAX_ZAHREG - 1)) << 5) |		\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
 /* Vector lengths pseudo-register: */
 #define KVM_REG_ARM64_SME_VLS		(KVM_REG_ARM64 | KVM_REG_ARM64_SME | \
 					 KVM_REG_SIZE_U512 | 0xffff)
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 5f2845625c55..cb38af891387 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -573,22 +573,113 @@ static int set_sme_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	return set_vec_vls(ARM64_VEC_SME, vcpu, reg);
 }
 
+/*
+ * Validate SVE register ID and get sanitised bounds for user/kernel SVE
+ * register copy
+ */
+static int sme_reg_to_region(struct vec_state_reg_region *region,
+			     struct kvm_vcpu *vcpu,
+			     const struct kvm_one_reg *reg)
+{
+	/* reg ID ranges for ZA.H[n] registers */
+	unsigned int vq = vcpu_sme_max_vq(vcpu) - 1;
+	const u64 za_h_max = vq * __SVE_VQ_BYTES;
+	const u64 zah_id_min = KVM_REG_ARM64_SME_ZAHREG(0, 0);
+	const u64 zah_id_max = KVM_REG_ARM64_SME_ZAHREG(za_h_max - 1,
+						       SVE_NUM_SLICES - 1);
+
+	unsigned int reg_num;
+
+	unsigned int reqoffset, reqlen; /* User-requested offset and length */
+	unsigned int maxlen; /* Maximum permitted length */
+
+	size_t sme_state_size;
+
+	reg_num = (reg->id & SVE_REG_ID_MASK) >> SVE_REG_ID_SHIFT;
+
+	if (reg->id >= zah_id_min && reg->id <= zah_id_max) {
+		/* ZA is exposed as SVE vectors ZA.H[n] */
+		if (!vcpu_has_sme(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
+			return -ENOENT;
+
+		reqoffset = ZA_SIG_ZAV_OFFSET(vq, reg_num) -
+			ZA_SIG_REGS_OFFSET;
+		reqlen = KVM_SVE_ZREG_SIZE;
+		maxlen = SVE_SIG_ZREG_SIZE(vq);
+	} else {
+		return -EINVAL;
+	}
+
+	sme_state_size = vcpu_sme_state_size(vcpu);
+	if (WARN_ON(!sme_state_size))
+		return -EINVAL;
+
+	region->koffset = array_index_nospec(reqoffset, sme_state_size);
+	region->klen = min(maxlen, reqlen);
+	region->upad = reqlen - region->klen;
+
+	return 0;
+}
+
+/*
+ * ZA is exposed as an array of horizontal vectors with the same
+ * format as SVE, mirroring the architecture's LDR ZA[Wv, offs], [Xn]
+ * instruction.
+ */
+
 static int get_sme_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
+	int ret;
+	struct vec_state_reg_region region;
+	char __user *uptr = (char __user *)reg->addr;
+
 	/* Handle the KVM_REG_ARM64_SME_VLS pseudo-reg as a special case: */
 	if (reg->id == KVM_REG_ARM64_SME_VLS)
 		return get_sme_vls(vcpu, reg);
 
-	return -EINVAL;
+	/* Try to interpret reg ID as an architectural SVE register... */
+	ret = sme_reg_to_region(&region, vcpu, reg);
+	if (ret)
+		return ret;
+
+	/* Try to interpret reg ID as an architectural SVE register... */
+	ret = sme_reg_to_region(&region, vcpu, reg);
+	if (ret)
+		return ret;
+
+	if (!kvm_arm_vcpu_vec_finalized(vcpu))
+		return -EPERM;
+
+	if (copy_from_user(vcpu->arch.sme_state + region.koffset, uptr,
+			   region.klen))
+		return -EFAULT;
+
+	return 0;
 }
 
 static int set_sme_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
+	int ret;
+	struct vec_state_reg_region region;
+	char __user *uptr = (char __user *)reg->addr;
+
 	/* Handle the KVM_REG_ARM64_SME_VLS pseudo-reg as a special case: */
 	if (reg->id == KVM_REG_ARM64_SME_VLS)
 		return set_sme_vls(vcpu, reg);
 
-	return -EINVAL;
+	/* Try to interpret reg ID as an architectural SVE register... */
+	ret = sme_reg_to_region(&region, vcpu, reg);
+	if (ret)
+		return ret;
+
+	if (!kvm_arm_vcpu_vec_finalized(vcpu))
+		return -EPERM;
+
+	if (copy_from_user(vcpu->arch.sme_state + region.koffset, uptr,
+			   region.klen))
+		return -EFAULT;
+
+	return 0;
 }
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {

-- 
2.30.2

