KVM: arm/arm64: vgic: Implement VGICv3 CPU interface access

VGICv3 CPU interface registers are accessed using
KVM_DEV_ARM_VGIC_CPU_SYSREGS ioctl. These registers are accessed
as 64-bit. The cpu MPIDR value is passed along with register id.
It is used to identify the cpu for registers access.

The VM that supports SEIs expect it on destination machine to handle
guest aborts and hence checked for ICC_CTLR_EL1.SEIS compatibility.
Similarly, VM that supports Affinity Level 3 that is required for AArch64
mode, is required to be supported on destination machine. Hence checked
for ICC_CTLR_EL1.A3V compatibility.

The arch/arm64/kvm/vgic-sys-reg-v3.c handles read and write of VGIC
CPU registers for AArch64.

For AArch32 mode, arch/arm/kvm/vgic-v3-coproc.c file is created but
APIs are not implemented.

Updated arch/arm/include/uapi/asm/kvm.h with new definitions
required to compile for AArch32.

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

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

2 files changed, 348 insertions, 1 deletions

diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index e025beceda39..afd51bebb9c5 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-ccflags-y += -Iarch/arm64/kvm
+ccflags-y += -Iarch/arm64/kvm -Ivirt/kvm/arm/vgic
 CFLAGS_arm.o := -I.
 CFLAGS_mmu.o := -I.
 
@@ -19,6 +19,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
 kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
+kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o
 
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
new file mode 100644
index 000000000000..79f37e37d367
--- /dev/null
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -0,0 +1,346 @@
+/*
+ * VGIC system registers handling functions for AArch64 mode
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include "vgic.h"
+#include "sys_regs.h"
+
+static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	u32 host_pri_bits, host_id_bits, host_seis, host_a3v, seis, a3v;
+	struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_vmcr vmcr;
+	u64 val;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (p->is_write) {
+		val = p->regval;
+
+		/*
+		 * Disallow restoring VM state if not supported by this
+		 * hardware.
+		 */
+		host_pri_bits = ((val & ICC_CTLR_EL1_PRI_BITS_MASK) >>
+				 ICC_CTLR_EL1_PRI_BITS_SHIFT) + 1;
+		if (host_pri_bits > vgic_v3_cpu->num_pri_bits)
+			return false;
+
+		vgic_v3_cpu->num_pri_bits = host_pri_bits;
+
+		host_id_bits = (val & ICC_CTLR_EL1_ID_BITS_MASK) >>
+				ICC_CTLR_EL1_ID_BITS_SHIFT;
+		if (host_id_bits > vgic_v3_cpu->num_id_bits)
+			return false;
+
+		vgic_v3_cpu->num_id_bits = host_id_bits;
+
+		host_seis = ((kvm_vgic_global_state.ich_vtr_el2 &
+			     ICH_VTR_SEIS_MASK) >> ICH_VTR_SEIS_SHIFT);
+		seis = (val & ICC_CTLR_EL1_SEIS_MASK) >>
+			ICC_CTLR_EL1_SEIS_SHIFT;
+		if (host_seis != seis)
+			return false;
+
+		host_a3v = ((kvm_vgic_global_state.ich_vtr_el2 &
+			    ICH_VTR_A3V_MASK) >> ICH_VTR_A3V_SHIFT);
+		a3v = (val & ICC_CTLR_EL1_A3V_MASK) >> ICC_CTLR_EL1_A3V_SHIFT;
+		if (host_a3v != a3v)
+			return false;
+
+		/*
+		 * Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
+		 * The vgic_set_vmcr() will convert to ICH_VMCR layout.
+		 */
+		vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
+		vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+		vgic_set_vmcr(vcpu, &vmcr);
+	} else {
+		val = 0;
+		val |= (vgic_v3_cpu->num_pri_bits - 1) <<
+			ICC_CTLR_EL1_PRI_BITS_SHIFT;
+		val |= vgic_v3_cpu->num_id_bits << ICC_CTLR_EL1_ID_BITS_SHIFT;
+		val |= ((kvm_vgic_global_state.ich_vtr_el2 &
+			ICH_VTR_SEIS_MASK) >> ICH_VTR_SEIS_SHIFT) <<
+			ICC_CTLR_EL1_SEIS_SHIFT;
+		val |= ((kvm_vgic_global_state.ich_vtr_el2 &
+			ICH_VTR_A3V_MASK) >> ICH_VTR_A3V_SHIFT) <<
+			ICC_CTLR_EL1_A3V_SHIFT;
+		/*
+		 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
+		 * Extract it directly using ICC_CTLR_EL1 reg definitions.
+		 */
+		val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
+		val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+
+		p->regval = val;
+	}
+
+	return true;
+}
+
+static bool access_gic_pmr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	struct vgic_vmcr vmcr;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (p->is_write) {
+		vmcr.pmr = (p->regval & ICC_PMR_EL1_MASK) >> ICC_PMR_EL1_SHIFT;
+		vgic_set_vmcr(vcpu, &vmcr);
+	} else {
+		p->regval = (vmcr.pmr << ICC_PMR_EL1_SHIFT) & ICC_PMR_EL1_MASK;
+	}
+
+	return true;
+}
+
+static bool access_gic_bpr0(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	struct vgic_vmcr vmcr;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (p->is_write) {
+		vmcr.bpr = (p->regval & ICC_BPR0_EL1_MASK) >>
+			    ICC_BPR0_EL1_SHIFT;
+		vgic_set_vmcr(vcpu, &vmcr);
+	} else {
+		p->regval = (vmcr.bpr << ICC_BPR0_EL1_SHIFT) &
+			     ICC_BPR0_EL1_MASK;
+	}
+
+	return true;
+}
+
+static bool access_gic_bpr1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	struct vgic_vmcr vmcr;
+
+	if (!p->is_write)
+		p->regval = 0;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+		if (p->is_write) {
+			vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
+				     ICC_BPR1_EL1_SHIFT;
+			vgic_set_vmcr(vcpu, &vmcr);
+		} else {
+			p->regval = (vmcr.abpr << ICC_BPR1_EL1_SHIFT) &
+				     ICC_BPR1_EL1_MASK;
+		}
+	} else {
+		if (!p->is_write)
+			p->regval = min((vmcr.bpr + 1), 7U);
+	}
+
+	return true;
+}
+
+static bool access_gic_grpen0(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	struct vgic_vmcr vmcr;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (p->is_write) {
+		vmcr.grpen0 = (p->regval & ICC_IGRPEN0_EL1_MASK) >>
+			       ICC_IGRPEN0_EL1_SHIFT;
+		vgic_set_vmcr(vcpu, &vmcr);
+	} else {
+		p->regval = (vmcr.grpen0 << ICC_IGRPEN0_EL1_SHIFT) &
+			     ICC_IGRPEN0_EL1_MASK;
+	}
+
+	return true;
+}
+
+static bool access_gic_grpen1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	struct vgic_vmcr vmcr;
+
+	vgic_get_vmcr(vcpu, &vmcr);
+	if (p->is_write) {
+		vmcr.grpen1 = (p->regval & ICC_IGRPEN1_EL1_MASK) >>
+			       ICC_IGRPEN1_EL1_SHIFT;
+		vgic_set_vmcr(vcpu, &vmcr);
+	} else {
+		p->regval = (vmcr.grpen1 << ICC_IGRPEN1_EL1_SHIFT) &
+			     ICC_IGRPEN1_EL1_MASK;
+	}
+
+	return true;
+}
+
+static void vgic_v3_access_apr_reg(struct kvm_vcpu *vcpu,
+				   struct sys_reg_params *p, u8 apr, u8 idx)
+{
+	struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3;
+	uint32_t *ap_reg;
+
+	if (apr)
+		ap_reg = &vgicv3->vgic_ap1r[idx];
+	else
+		ap_reg = &vgicv3->vgic_ap0r[idx];
+
+	if (p->is_write)
+		*ap_reg = p->regval;
+	else
+		p->regval = *ap_reg;
+}
+
+static bool access_gic_aprn(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r, u8 apr)
+{
+	struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu;
+	u8 idx = r->Op2 & 3;
+
+	/*
+	 * num_pri_bits are initialized with HW supported values.
+	 * We can rely safely on num_pri_bits even if VM has not
+	 * restored ICC_CTLR_EL1 before restoring APnR registers.
+	 */
+	switch (vgic_v3_cpu->num_pri_bits) {
+	case 7:
+		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
+		break;
+	case 6:
+		if (idx > 1)
+			goto err;
+		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
+		break;
+	default:
+		if (idx > 0)
+			goto err;
+		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
+	}
+
+	return true;
+err:
+	if (!p->is_write)
+		p->regval = 0;
+
+	return false;
+}
+
+static bool access_gic_ap0r(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+
+{
+	return access_gic_aprn(vcpu, p, r, 0);
+}
+
+static bool access_gic_ap1r(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	return access_gic_aprn(vcpu, p, r, 1);
+}
+
+static bool access_gic_sre(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	/* Validate SRE bit */
+	if (p->is_write) {
+		if (!(p->regval & ICC_SRE_EL1_SRE))
+			return false;
+	} else {
+		p->regval = vgicv3->vgic_sre;
+	}
+
+	return true;
+}
+static const struct sys_reg_desc gic_v3_icc_reg_descs[] = {
+	/* ICC_PMR_EL1 */
+	{ Op0(3), Op1(0), CRn(4), CRm(6), Op2(0), access_gic_pmr },
+	/* ICC_BPR0_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(3), access_gic_bpr0 },
+	/* ICC_AP0R0_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(4), access_gic_ap0r },
+	/* ICC_AP0R1_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(5), access_gic_ap0r },
+	/* ICC_AP0R2_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(6), access_gic_ap0r },
+	/* ICC_AP0R3_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(7), access_gic_ap0r },
+	/* ICC_AP1R0_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(0), access_gic_ap1r },
+	/* ICC_AP1R1_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(1), access_gic_ap1r },
+	/* ICC_AP1R2_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(2), access_gic_ap1r },
+	/* ICC_AP1R3_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(3), access_gic_ap1r },
+	/* ICC_BPR1_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(3), access_gic_bpr1 },
+	/* ICC_CTLR_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(4), access_gic_ctlr },
+	/* ICC_SRE_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(5), access_gic_sre },
+	/* ICC_IGRPEN0_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(6), access_gic_grpen0 },
+	/* ICC_GRPEN1_EL1 */
+	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(7), access_gic_grpen1 },
+};
+
+int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id,
+				u64 *reg)
+{
+	struct sys_reg_params params;
+	u64 sysreg = (id & KVM_DEV_ARM_VGIC_SYSREG_MASK) | KVM_REG_SIZE_U64;
+
+	params.regval = *reg;
+	params.is_write = is_write;
+	params.is_aarch32 = false;
+	params.is_32bit = false;
+
+	if (find_reg_by_id(sysreg, &params, gic_v3_icc_reg_descs,
+			      ARRAY_SIZE(gic_v3_icc_reg_descs)))
+		return 0;
+
+	return -ENXIO;
+}
+
+int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id,
+				u64 *reg)
+{
+	struct sys_reg_params params;
+	const struct sys_reg_desc *r;
+	u64 sysreg = (id & KVM_DEV_ARM_VGIC_SYSREG_MASK) | KVM_REG_SIZE_U64;
+
+	if (is_write)
+		params.regval = *reg;
+	params.is_write = is_write;
+	params.is_aarch32 = false;
+	params.is_32bit = false;
+
+	r = find_reg_by_id(sysreg, &params, gic_v3_icc_reg_descs,
+			   ARRAY_SIZE(gic_v3_icc_reg_descs));
+	if (!r)
+		return -ENXIO;
+
+	if (!r->access(vcpu, &params, r))
+		return -EINVAL;
+
+	if (!is_write)
+		*reg = params.regval;
+
+	return 0;
+}