diff mbox series

[v8,18/69] KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor

Message ID 20230131092504.2880505-19-maz@kernel.org (mailing list archive)
State New, archived
Headers show
Series KVM: arm64: ARMv8.3/8.4 Nested Virtualization support | expand

Commit Message

Marc Zyngier Jan. 31, 2023, 9:24 a.m. UTC 
We can no longer blindly copy the VCPU's PSTATE into SPSR_EL2 and return
to the guest and vice versa when taking an exception to the hypervisor,
because we emulate virtual EL2 in EL1 and therefore have to translate
the mode field from EL2 to EL1 and vice versa.

This requires keeping track of the state we enter the guest, for which
we transiently use a dedicated flag.

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          |  2 ++
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 19 ++++++++++++++++-
 arch/arm64/kvm/hyp/vhe/switch.c            | 24 ++++++++++++++++++++++
 3 files changed, 44 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 640997251724..a1892a8f6032 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -649,6 +649,8 @@  struct kvm_vcpu_arch {
 #define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
 /* Save TRBE context if active  */
 #define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
+/* vcpu running in HYP context */
+#define VCPU_HYP_CONTEXT	__vcpu_single_flag(iflags, BIT(7))
 
 /* SVE enabled for host EL0 */
 #define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index c506eabc4e21..d67c620f2af7 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -155,9 +155,26 @@  static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
 	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
 }
 
+/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */
+static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt)
+{
+	u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	}
+
+	return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+}
+
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	u64 pstate = ctxt->regs.pstate;
+	u64 pstate = to_hw_pstate(ctxt);
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
 
 	/*
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 81bf236d9c27..cd3f3117bf16 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -120,6 +120,25 @@  static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 
 static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * If we were in HYP context on entry, adjust the PSTATE view
+	 * so that the usual helpers work correctly.
+	 */
+	if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) {
+		u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+		switch (mode) {
+		case PSR_MODE_EL1t:
+			mode = PSR_MODE_EL2t;
+			break;
+		case PSR_MODE_EL1h:
+			mode = PSR_MODE_EL2h;
+			break;
+		}
+
+		*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
+		*vcpu_cpsr(vcpu) |= mode;
+	}
 }
 
 /* Switch to the guest for VHE systems running in EL2 */
@@ -154,6 +173,11 @@  static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
+	if (is_hyp_ctxt(vcpu))
+		vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT);
+	else
+		vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT);
+
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);