[PATCH v3 14/66] KVM: arm64: nv: Handle SPSR_EL2 specially

[Marc Zyngier]

SPSR_EL2 needs special attention when running nested on ARMv8.3:

If taking an exception while running at vEL2 (actually EL1), the
HW will update the SPSR_EL1 register with the EL1 mode. We need
to track this in order to make sure that accesses to the virtual
view of SPSR_EL2 is correct.

To do so, we place an illegal value in SPSR_EL1.M, and patch it
accordingly if required when accessing it.

Signed-off-by: Marc Zyngier <maz at kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 37 ++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c            | 23 +++++++++++++++--
 2 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index deffd3cc4443..5c7dc659e8c4 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -238,6 +238,43 @@ static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 	return __is_hyp_ctxt(&vcpu->arch.ctxt);
 }
 
+static inline u64 __fixup_spsr_el2_write(struct kvm_cpu_context *ctxt, u64 val)
+{
+	if (!__vcpu_el2_e2h_is_set(ctxt)) {
+		/*
+		 * Clear the .M field when writing SPSR to the CPU, so that we
+		 * can detect when the CPU clobbered our SPSR copy during a
+		 * local exception.
+		 */
+		val &= ~0xc;
+	}
+
+	return val;
+}
+
+static inline u64 __fixup_spsr_el2_read(const struct kvm_cpu_context *ctxt, u64 val)
+{
+	if (__vcpu_el2_e2h_is_set(ctxt))
+		return val;
+
+	/*
+	 * SPSR.M == 0 means the CPU has not touched the SPSR, so the
+	 * register has still the value we saved on the last write.
+	 */
+	if ((val & 0xc) == 0)
+		return ctxt_sys_reg(ctxt, SPSR_EL2);
+
+	/*
+	 * Otherwise there was a "local" exception on the CPU,
+	 * which from the guest's point of view was being taken from
+	 * EL2 to EL2, although it actually happened to be from
+	 * EL1 to EL1.
+	 * So we need to fix the .M field in SPSR, to make it look
+	 * like EL2, which is what the guest would expect.
+	 */
+	return (val & ~0x0c) | CurrentEL_EL2;
+}
+
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d5a855cb65ca..77a2d452b79d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -133,11 +133,14 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 			goto memory_read;
 
 		/*
-		 * ELR_EL2 is special cased for now.
+		 * ELR_EL2 and SPSR_EL2 are special cased for now.
 		 */
 		switch (reg) {
 		case ELR_EL2:
 			return read_sysreg_el1(SYS_ELR);
+		case SPSR_EL2:
+			val = read_sysreg_el1(SYS_SPSR);
+			return __fixup_spsr_el2_read(&vcpu->arch.ctxt, val);
 		}
 
 		/*
@@ -194,6 +197,10 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		case ELR_EL2:
 			write_sysreg_el1(val, SYS_ELR);
 			return;
+		case SPSR_EL2:
+			val = __fixup_spsr_el2_write(&vcpu->arch.ctxt, val);
+			write_sysreg_el1(val, SYS_SPSR);
+			return;
 		}
 
 		/* No EL1 counterpart? We're done here.? */
@@ -1527,6 +1534,18 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_spsr_el2(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, SPSR_EL2);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -1923,7 +1942,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_VTCR_EL2), access_rw, reset_val, VTCR_EL2, 0 },
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
-	{ SYS_DESC(SYS_SPSR_EL2), access_rw, reset_val, SPSR_EL2, 0 },
+	{ SYS_DESC(SYS_SPSR_EL2), access_spsr_el2, reset_val, SPSR_EL2, 0 },
 	{ SYS_DESC(SYS_ELR_EL2), access_rw, reset_val, ELR_EL2, 0 },
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
 
-- 
2.29.2