From: Marc Zyngier maz@kernel.org
commit 26778aaa134a9aefdf5dbaad904054d7be9d656d upstream.
KVM currently updates PC (and the corresponding exception state) using a two phase approach: first by setting a set of flags, then by converting these flags into a state update when the vcpu is about to enter the guest.
However, this creates a disconnect with userspace if the vcpu thread returns there with any exception/PC flag set. In this case, the exposed context is wrong, as userspace doesn't have access to these flags (they aren't architectural). It also means that these flags are preserved across a reset, which isn't expected.
To solve this problem, force an explicit synchronisation of the exception state on vcpu exit to userspace. As an optimisation for nVHE systems, only perform this when there is something pending.
Reported-by: Zenghui Yu yuzenghui@huawei.com Reviewed-by: Alexandru Elisei alexandru.elisei@arm.com Reviewed-by: Zenghui Yu yuzenghui@huawei.com Tested-by: Zenghui Yu yuzenghui@huawei.com Signed-off-by: Marc Zyngier maz@kernel.org Cc: stable@vger.kernel.org # 5.11 [yuz: stable-5.12.y backport: allocate a new number (15) for __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc to keep the host_hcall array tightly packed] Signed-off-by: Zenghui Yu yuzenghui@huawei.com Reviewed-by: Marc Zyngier maz@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/include/asm/kvm_asm.h | 1 + arch/arm64/kvm/arm.c | 11 +++++++++++ arch/arm64/kvm/hyp/exception.c | 4 ++-- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 8 ++++++++ 4 files changed, 22 insertions(+), 2 deletions(-)
--- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -57,6 +57,7 @@ #define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 12 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs 13 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs 14 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 15
#ifndef __ASSEMBLY__
--- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -892,6 +892,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
kvm_sigset_deactivate(vcpu);
+ /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -331,8 +331,8 @@ static void kvm_inject_exception(struct }
/* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. */ void __kvm_adjust_pc(struct kvm_vcpu *vcpu) { --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -25,6 +25,13 @@ static void handle___kvm_vcpu_run(struct cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); }
+static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -112,6 +119,7 @@ typedef void (*hcall_t)(struct kvm_cpu_c
static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid),